METHOD AND SYSTEM FOR LAYERED WOOD PRODUCT PRODUCTION

20210398270 · 2021-12-23

Assignee

Inventors

Cpc classification

International classification

Abstract

Irregularities on the surfaces of veneer, such as full veneer sheets and/or veneer core material are detected using Near InfraRed (NIR) technology, including Near InfraRed/Short Wave InfraRed (NIR/SWIR) cameras and detectors. A grade is then assigned to the veneer based, at least in part, on the detected irregularities. The graded veneer is then stacked based, at least in part, on the grade assigned to the veneer. The graded veneer stacks are then provided to local robotic panel assembly and pressing systems that include one or more local robotic panel assembly cells for processing the veneer into layered wood product panels.

Claims

1. A system for producing layered wood products comprising: a veneer analysis system including an NIR analysis system for inspecting the veneer and assigning a grade to the veneer; one or more veneer inspection/grading robots, the one or more veneer inspection/grading robots retrieving veneer from a stack of veneer and presenting the veneer to the veneer analysis system in accordance with received control signals, the one or more veneer inspection/grading robots then placing the veneer onto one of two or more graded veneer stacks according to the grade assigned to the veneer by the veneer analysis system; a robotic panel assembly cell, the robotic panel assembly cell producing a stack of green layered wood product panels using veneer from the two or more graded veneer stacks; a pre-press, the pre-press pressing the stack of green layered wood product panels to produce pre-pressed layered wood product panels; and a hot press, the hot press heating and pressing the pre-pressed layered wood product panels to produce cured layered wood product panels.

2. The system of claim 1 wherein the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a green layered wood product panel stack in accordance with received control signals; one or more glue application robots, the one or more glue application robots applying a layer of glue between sheets of veneer in the green layered wood product panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots and the one or more glue application robots and directing the one or more veneer handling robots and the one or more glue application robots in the construction of the green layered wood product panel stack via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

3. The system of claim 2 wherein the veneer analysis system includes a visual light imaging system for analysis of wood products.

4. The system of claim 2 wherein the local robotic panel assembly and pressing station is used to produce a plywood panel stack and the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a green plywood panel stack in accordance with received control signals; one or more core handling robots, the one or more core handling robots retrieving core material from a core material stack of the two or more graded veneer stacks and placing the core material on the green plywood panel stack in accordance with received control signals; one or more glue application robots, the one or more glue application robots applying a layer of glue between sheets of veneer and layers of core material in the green plywood panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots and directing the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots in the construction of the green plywood panel stack via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

5. The system of claim 4 wherein the green plywood panel stack includes two or more individual green plywood panels.

6. The system claim 2 wherein the local robotic panel assembly and pressing station is used to produce Parallel-Laminated Veneer (PLV) panel stacks and the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a on a green PLV panel stack in accordance with received control signals; one or more glue application robots for applying a layer of glue between sheets of veneer in the green PLV panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots and the one or more glue application robots and directing the one or more veneer handling robots and the one or more glue application robots in the construction of the green PLV panel stacks via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

7. The system of claim 6 wherein the green PLV panel stack includes two or more individual green PLV panels.

8. The system of claim 1 wherein the NIR analysis system includes: a surface irregularity level to greyscale mapping database, the surface irregularity level to greyscale mapping database containing mapping data that maps surface irregularities to Near InfraRed (NIR) image greyscale values for veneer; one or more sources of illumination positioned to illuminate a veneer surface, the NIR analysis system including one or more NIR cameras positioned to capture one or more NIR images of the illuminated veneer surface; a physical memory, the physical memory including NIR image data representing one or more NIR images of the illuminated surface of the veneer captured using the one or more NIR cameras; one or more processors for processing the data representing one or more NIR images of the illuminated surface of the veneer to generate NIR greyscale image data indicating irregularities in the illuminated surface of the veneer; one or processors for processing the NIR greyscale image data using the surface irregularity level to greyscale mapping database data to identify irregularities for the surface of the veneer; and a grade assignment module for generating grading data representing a grade assigned to the veneer based on the identified irregularities for the surface of the veneer.

9. A system for producing layered wood products comprising: an NIR analysis system for inspecting the veneer and assigning a grade to the veneer, the NIR analysis system including: a surface irregularity level to greyscale mapping database, the surface irregularity level to greyscale mapping database containing mapping data that maps surface irregularities to Near InfraRed (NIR) image greyscale values for veneer; one or more sources of illumination positioned to illuminate a veneer surface, the NIR analysis system including one or more NIR cameras positioned to capture one or more NIR images of the illuminated veneer surface; a physical memory, the physical memory including NIR image data representing one or more NIR images of the illuminated surface of the veneer captured using the one or more NIR cameras; one or more processors for processing the data representing one or more NIR images of the illuminated surface of the veneer to generate NIR greyscale image data indicating irregularities in the illuminated surface of the veneer; one or processors for processing the NIR greyscale image data using the surface irregularity level to greyscale mapping database data to identify irregularities for the surface of the veneer; and a grade assignment module for generating grading data representing a grade assigned to the veneer based on the identified irregularities for the surface of the veneer; one or more veneer inspection/grading robots, the one or more veneer inspection/grading robots retrieving veneer from a stack of veneer and presenting the veneer to the NIR analysis system in accordance with received control signals, the one or more veneer inspection/grading robots then placing the veneer onto one of two or more graded veneer stacks according to the grade assigned to the veneer by the NIR analysis system; a robotic panel assembly cell, the robotic panel assembly cell producing a stack of green layered wood product panels using veneer from the two or more graded veneer stacks; a pre-press, the pre-press pressing the stack of green layered wood product panels to produce pre-pressed layered wood product panels; and a hot press, the hot press heating and pressing the pre-pressed layered wood product panels to produce cured layered wood product panels.

10. The system of claim 9 wherein the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a green layered wood product panel stack in accordance with received control signals; one or more glue application robots, the one or more glue application robots applying a layer of glue between sheets of veneer in the green layered wood product panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots and the one or more glue application robots and directing the one or more veneer handling robots and the one or more glue application robots in the construction of the green layered wood product panel stack via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

11. The system of claim 9 wherein the local robotic panel assembly and pressing station is used to produce a plywood panel stack and the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a green plywood panel stack in accordance with received control signals; one or more core handling robots, the one or more core handling robots retrieving core material from a core material stack of the two or more graded veneer stacks and placing the core material on the green plywood panel stack in accordance with received control signals; one or more glue application robots, the one or more glue application robots applying a layer of glue between sheets of veneer and layers of core material in the green plywood panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots and directing the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots in the construction of the green plywood panel stack via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

12. The system of claim 11 wherein the green plywood panel stack includes two or more individual green plywood panels.

13. The system claim 9 wherein the local robotic panel assembly and pressing station is used to produce Parallel-Laminated Veneer (PLV) panel stacks and the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a on a green PLV panel stack in accordance with received control signals; one or more glue application robots for applying a layer of glue between sheets of veneer in the green PLV panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots and the one or more glue application robots and directing the one or more veneer handling robots and the one or more glue application robots in the construction of the green PLV panel stacks via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

14. The system of claim 13 wherein the green PLV panel stack includes two or more individual green PLV panels.

15. The system of claim 6 further comprising a visual light imaging system for analysis of wood products.

16. A method for producing layered wood products comprising: providing veneer to a veneer analysis system including an NIR analysis system for inspecting the veneer and assigning a grade to the veneer; providing one or more veneer inspection/grading robots; using one or more veneer inspection/grading robots to retrieve veneer from a stack of veneer and present the veneer to the veneer analysis system in accordance with received control signals, using the one or more veneer inspection/grading robots to place the veneer onto one of two or more graded veneer stacks according to the grade assigned to the veneer by the veneer analysis system; providing a robotic panel assembly cell; using the robotic panel assembly cell to produce a stack of green layered wood product panels using veneer from the two or more graded veneer stacks; providing a pre-press; using the pre-press to press the stack of green layered wood product panels to produce pre-pressed layered wood product panels; providing a hot press; and using the hot press heating and pressing the pre-pressed layered wood product panels to produce cured layered wood product panels.

17. The method of claim 16 wherein the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a green layered wood product panel stack in accordance with received control signals; one or more glue application robots, the one or more glue application robots applying a layer of glue between sheets of veneer in the green layered wood product panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots and the one or more glue application robots and directing the one or more veneer handling robots and the one or more glue application robots in the construction of the green layered wood product panel stack via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

18. The method of claim 16 wherein the local robotic panel assembly and pressing station is used to produce a plywood panel stack and the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a green plywood panel stack in accordance with received control signals; one or more core handling robots, the one or more core handling robots retrieving core material from a core material stack and placing the core material on the green plywood panel stack in accordance with received control signals; one or more glue application robots, the one or more glue application robots applying a layer of glue between sheets of veneer and layers of core material in the green plywood panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots and directing the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots in the construction of the green plywood panel stack via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

19. The method of claim 16 wherein the local robotic panel assembly and pressing station is used to produce Parallel-Laminated Veneer (PLV) panel stacks and the robotic panel assembly cell includes: one or more veneer handling robots, the one or more veneer handling robots retrieving veneer sheets from the two or more graded veneer stacks and placing the veneer sheets on a on a green PLV panel stack in accordance with received control signals; one or more glue application robots for applying a layer of glue between sheets of veneer in the green PLV panel stack in accordance with received control signals; and a control system for controlling the one or more veneer handling robots and the one or more glue application robots and directing the one or more veneer handling robots and the one or more glue application robots in the construction of the green PLV panel stacks via control signals sent to the one or more veneer handling robots and the one or more glue application robots.

20. The method of claim 16 wherein the NIR analysis system includes: a surface irregularity level to greyscale mapping database, the surface irregularity level to greyscale mapping database containing mapping data that maps surface irregularities to Near InfraRed (NIR) image greyscale values for veneer; one or more sources of illumination positioned to illuminate a veneer surface, the NIR analysis system including one or more NIR cameras positioned to capture one or more NIR images of the illuminated veneer surface; a physical memory, the physical memory including NIR image data representing one or more NIR images of the illuminated surface of the veneer captured using the one or more NIR cameras; one or more processors for processing the data representing one or more NIR images of the illuminated surface of the veneer to generate NIR greyscale image data indicating irregularities in the illuminated surface of the veneer; one or processors for processing the NIR greyscale image data using the surface irregularity level to greyscale mapping database data to identify irregularities for the surface of the veneer; and a grade assignment module for generating grading data representing a grade assigned to the veneer based on the identified irregularities for the surface of the veneer.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0173] The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

[0174] FIG. 1 shows a preconditioned wood source, in this example a peeler log, being processed using rotary cutting methods.

[0175] FIG. 2A is a representation of a magnified side view of a surface of veneer that was produced from an optimally preconditioned conditioned log.

[0176] FIG. 2B is a representation of a magnified surface of veneer that was produced from an over preconditioned log.

[0177] FIG. 2C is a representation of a magnified side view of a surface of veneer that was produced from an under preconditioned log.

[0178] FIG. 2D is a representation of a magnified view of a surface of veneer that was produced under conditions where the cutting knife edge was irregular, nicked, or otherwise damaged.

[0179] FIG. 2E is a representation of a magnified side view of a surface of veneer that was produced under conditions where the cutting knife edge was not held against the surface of the preconditioned log with a steady pressure.

[0180] FIG. 2F is a representation of a magnified side view of a surface of veneer that was produced under conditions where the cutting knife was dull.

[0181] FIG. 3A is a diagram representing traditional layered wood product panel assembly layup station.

[0182] FIG. 3B is a diagram representing a side view of the formation of layers, or plys, being created using a traditional layered wood product panel assembly layup station.

[0183] FIG. 3C is a diagram representing a traditional layered wood product panel assembly layup line including five traditional layered wood product panel assembly layup stations.

[0184] FIG. 3D is a diagram representing a traditional layered wood product panel assembly layup and press line including the traditional layered wood product panel assembly layup line of FIG. 1D and a press area including four pressing stations.

[0185] FIG. 4A is simplified block diagram of a system for detecting surface irregularity levels in veneer using NIR technology in accordance with one embodiment.

[0186] FIG. 4B shows an end view of veneer positioned in an NIR analysis station including three NIR cameras.

[0187] FIG. 4C is a representation of an NIR image of the surface of veneer that was produced from an optimally preconditioned conditioned log.

[0188] FIG. 4D is a representation of an NIR image of the surface of veneer that was produced from an over preconditioned log.

[0189] FIG. 4E is a representation of an NIR image of the surface of veneer that was produced from an under preconditioned log.

[0190] FIG. 4F is a representation of an NIR image of the surface of veneer that was produced under conditions where the cutting knife edge was irregular, nicked, or otherwise damaged.

[0191] FIG. 4G is a representation of an NIR image of the surface of veneer that was produced under conditions where the cutting knife edge was not held against the surface of the preconditioned log with a steady pressure.

[0192] FIG. 4H is a representation of an NIR image of the surface of veneer that was produced under conditions where the cutting knife was dull.

[0193] FIG. 5 is flow chart of a process for detecting surface irregularity levels in veneer using NIR technology in accordance with one embodiment.

[0194] FIG. 6 is simplified block diagram of a system for detecting surface irregularity levels in veneer using NIR technology and machine learning methods in accordance with one embodiment.

[0195] FIG. 7 is flow chart of a process for detecting surface irregularity levels in veneer using NIR technology and machine learning methods in accordance with one embodiment.

[0196] FIG. 8 is simplified block diagram of a system for adjusting a preconditioning process of wood sources used to produce veneer based on a level of irregularity of a first surface of the veneer in accordance with one embodiment.

[0197] FIG. 9 is flow chart of a process for adjusting a preconditioning process of wood sources used to produce veneer based on a level of irregularity of a first surface of the veneer in accordance with one embodiment.

[0198] FIG. 10 is simplified block diagram of a system for adjusting processing parameters used to produce veneer from a wood source based on a level of irregularity of a first surface of the veneer in accordance with one embodiment.

[0199] FIG. 11 is flow chart of a process for adjusting processing parameters used to produce veneer from a wood source based on a level of irregularity of a first surface of the veneer in accordance with one embodiment.

[0200] FIG. 12A is a diagram of a local robotic panel assembly and pressing station in accordance with one embodiment.

[0201] FIG. 12B is a diagram of a robotic panel assembly and pressing system including four local robotic panel assembly and pressing stations in accordance with one embodiment.

[0202] FIG. 12C is a diagram of a robotic panel assembly cell of FIGS. 12A and 12B in accordance with one embodiment.

[0203] FIG. 12D is a diagram of a local robotic panel assembly cell of FIGS. 12A and 12B including a veneer inspection and grading system in accordance with one embodiment.

[0204] FIG. 13 is a diagram of a local robotic panel assembly and pressing station including a quality analysis and feedback cell for process refinement in accordance with one embodiment.

[0205] FIG. 14A is a photograph of a structural density analysis report based on the results of processing using one type of wood product panel bond analyzer used in accordance with one embodiment.

[0206] FIG. 14B is a photograph of average panel thickness analysis report based on the results of processing using one type of wood product panel bond analyzer used in accordance with one embodiment.

[0207] FIG. 14C is a photograph of panel thickness trend analysis report based on the results of processing using one type of wood product panel bond analyzer used in accordance with one embodiment.

[0208] Common reference numerals are used throughout the figures and the detailed description to indicate like elements. One skilled in the art will readily recognize that the above figures are merely illustrative examples and that other architectures, modes of operation, orders of operation, and elements/functions can be provided and implemented without departing from the characteristics and features of the invention, as set forth in the claims.

DETAILED DESCRIPTION

[0209] Embodiments will now be discussed with reference to the accompanying figures, which depict one or more exemplary embodiments. Embodiments may be implemented in many different forms and should not be construed as limited to the embodiments set forth herein, shown in the figures, or described below. Rather, these exemplary embodiments are provided to allow a complete disclosure that conveys the principles of the invention, as set forth in the claims, to those of skill in the art.

[0210] Embodiments of the present disclosure provide an effective and efficient technical solution to the long standing problem of providing a method and system for producing layered wood products that is more consistent, more effective, less expensive to operate, and more efficient.

[0211] In one embodiment, irregularities on the surfaces of veneer, such as full veneer sheets, veneer strips, and/or partial veneer sheets are detected using Near InfraRed (NIR) technology, including Near InfraRed/Short Wave InfraRed (NIR/SWIR) cameras and detectors. In one embodiment, a grade is then assigned to the veneer based, at least in part, on the detected irregularities. In one embodiment, the graded veneer is then stacked based, at least in part, on the grade assigned to the veneer. The graded veneer stacks are then provided to local robotic panel assembly and pressing systems that include one or more local robotic panel assembly cells for processing the veneer into layered wood product panels.

[0212] To this end, the disclosed embodiments utilize NIR analysis systems and NIR technology, including NIR cameras and detectors, to accurately identify surface irregularities and the specific locations of the irregularities in veneer surface.

[0213] As discussed in more detail below, in one embodiment, this is accomplished by providing a NIR analysis system including one or more illumination sources and one or more NIR cameras. In addition, in some embodiments, visual cameras may be combined to further refine the NIR image based on physical features such as knots that impact veneer ribbon peel quality, or thermal cameras that show temperature variations in the material temperature that impacts veneer ribbon peel quality peel quality.

[0214] Once the irregularity levels over the first surface of the veneer are identified, a grade is assigned to the veneer based on the identified irregularity levels for the veneer. In one embodiment, based, at least in part, on the grade assigned to the veneer, one or more actions are taken with respect to the veneer including, but not limited to, assigning the veneer to a specific veneer stack associated with the grade assigned to the veneer.

[0215] FIG. 4A is simplified block diagram of one embodiment of an NIR analysis system 400 for detecting surface irregularity levels in veneer using NIR technology in accordance with one embodiment.

[0216] In one embodiment, NIR analysis system 400 includes a production floor environment 401, including an NIR analysis station 420 and a computing environment 450. As discussed in more detail below, in one embodiment, NIR analysis system 400 is part of a veneer analysis system (not shown).

[0217] As seen in FIG. 4A, production floor environment 401 includes NIR analysis station 420 and selected action implementation module 496. As seen in FIG. 4A, NIR analysis station 420 includes one or more illumination sources, such as illumination source 422, positioned to illuminate a surface of veneer. In various embodiments, the one or more illumination sources, such as illumination source 422, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 422, can include, but are not limited to, halogen, halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0218] As seen in FIG. 4A, NIR analysis station 420 also includes one or more NIR cameras, such as NIR camera 424, positioned to capture NIR image data 462 representing one or more NIR images of the illuminated surface of the veneer. In one embodiment, the one or more NIR cameras, such as NIR camera 424, are adjustably positioned and adjustably focused to capture any desired one or more NIR images of the illuminated surface of the veneer.

[0219] As used herein, the terms Near InfraRed (NIR) and Short-Wave InfraRed (SWIR) are used interchangeably to include wavelengths in the range of 750 nanometers (nm) to 4500 nm. In addition, all stated wave lengths herein are assumed to include values within 10% of the stated value. NIR wavelengths are in the range of 750 nanometers (nm) to 4500 nm which are much smaller that the visible wavelengths of 480 to 740 nm. Consequently, the use of NIR cameras as disclosed herein results in resolutions and accuracy that simply cannot be achieved using traditional visual irregularity detection systems.

[0220] As seen in FIG. 4A, and as discussed below, veneer 430 to be analyzed in the NIR analysis station 420 is positioned in NIR analysis station 420. In various embodiments, the veneer 430 can be any veneer as discussed herein, and/or as known in the art at the time of filing and/or as becomes known after the time of filing.

[0221] In one embodiment, the veneer 430 to be analyzed is positioned such that a veneer first surface 432 of the veneer 430 to be analyzed is illuminated by the illumination source 422 and a sample portion of the veneer first surface 432 is within view and focus of NIR camera 424. In one embodiment, the veneer 430 is positioned in the NIR analysis station 420 by passing the veneer 430 through the NIR analysis station 420 on a conveyor system.

[0222] In various embodiments, the one or more NIR cameras, such as NIR camera 424, can be of any resolution desired. As noted above, when the one or more NIR cameras, such as NIR camera 424, are used to scan the veneer first surface 432 of veneer 430 for irregularities and create an NIR image data 462 of the veneer first surface 432, essentially each pixel generated by NIR camera 424 is a sample point. Consequently, the resolution and accuracy of the surface irregularity detection process is only limited by the number of pixels the NIR camera 424 has covering the field of view, e.g., the entire veneer first surface 432 of veneer 430. Consequently, in the case where NIR camera 424 is a 1.3 mega pixel camera, there are essentially 1,400,000 individual measurement points on the veneer first surface 432. In addition, NIR wavelengths are in the range of 750 nanometers (nm) to 4500 nm which are much smaller that the visible wavelengths of 480 to 740 nm. Consequently, using NIR cameras, such as NIR camera 424, results in resolutions and accuracy that simply cannot be achieved using traditional surface magnified visual image methods.

[0223] Therefore, using NIR cameras, such as NIR camera 424, NIR analysis system 400 is capable of detecting irregularities in a wide range of samples sizes ranging from of a traditional 2″×2″ square, to a full 4′×8′ sheet or panel surface, and, by using a series of NIR images spliced together, up to an 80′-120′ ribbon of material. This, in turn, allows the disclosed embodiments to be implemented without significantly slowing down the production process or increasing the cost of the finished veneer.

[0224] As seen in FIG. 4A, computing environment 450 includes computing system 452. As seen in FIG. 4A, in one embodiment, computing system 452 includes surface irregularity to greyscale mapping database 410 containing mapping data 412 that maps surface irregularities to Near InfraRed (NIR) image greyscale values for one or more full veneer sheet, veneer strip, and/or partial veneer sheets.

[0225] Using NIR images, extremely granular differences in irregularity levels can be detected. In general, locations with different levels of irregularities absorb/reflect different amounts of NIR radiation at specific frequencies. In operation, when NIR radiation of a given frequency is applied to a veneer first surface 432 of veneer 430, more NIR energy is reflected from surfaces that are perpendicular the NIR camera lens. Consequently, locations having irregularities such that the surfaces are not perpendicular the NIR camera lens will appear darker, i.e., have a greater greyscale value.

[0226] When the NIR camera 424 takes an image of the veneer first surface 432, the NIR camera 424 picks up the NIR energy reflected off veneer first surface 432 at angles of about 90 degrees, i.e., that are reflected substantially perpendicular to veneer first surface 432. Consequently, when the NIR camera 424 takes an image of the veneer first surface 432, the areas of irregularities, which scatter NIR energy at various angles other than 90 degrees and therefore reflect less NIR energy at the desired angles of about 90 degrees, appear darker than less textured areas. In addition, the higher or more significant the irregularities that are present, the darker the area appears because less NIR energy is reflected at angles of about 90 degrees to be captured by the NIR camera 424.

[0227] Using this fact, NIR image data 462 captured by the NIR camera 424 can be processed into NIR greyscale image data 464. Greyscale images can be of varying resolution, or bit, types. A 16-bit integer grayscale image provides 65535 available tonal steps from 0 (black) to 65535 (white). A 32-bit integer grayscale image theoretically will provide 4,294,967,295 tonal steps from 0 (black) to 4294967295 (white). Converting an NIR image based on these numbers of greyscale tonal steps results in a margin of error of significantly less than 0.1%.

[0228] In some embodiments, two or more illumination sources, such as illumination source 422, are utilized, that are positioned a different angles with respect to veneer first surface 432. This allows different types and levels of irregularities to be detected. In addition, using two or more two or more illumination sources, such as illumination source 422, that are positioned at different angles means that different irregularities will have surfaces perpendicular to the camera lens and therefore will yield a 3-D effect when a composite NIR image is constructed.

[0229] Likewise, in some embodiments, two or more NIR cameras are utilized, such as NIR camera 424, that are operated at different NIR frequencies and/or that are positioned a different angles with respect to veneer first surface 432. This allows different types and levels of irregularities to be detected. In addition, using two or more NIR cameras, such as NIR camera 424, that are positioned at different angles means that different irregularities will have surfaces perpendicular to the camera lens and therefore will yield a 3-D effect when a composite NIR image is constructed.

[0230] FIG. 4B shows an end view of veneer 430 positioned in an NIR analysis station including three NIR cameras 428, 424, and 426. As seen in FIG. 4B, first NIR camera 428 is positioned such that line 423 from a lens of first NIR camera 428 is at an angle “A” with respect to veneer first surface 432. Similarly, second NIR camera 424 is positioned such that line 425 from a lens of second NIR camera 424 is at an angle “B” with respect to veneer first surface 432. Likewise, third NIR camera 426 is positioned such that line 427 from a lens of third NIR camera 426 is at an angle “C” with respect to veneer first surface 432.

[0231] In some embodiments, each of NIR cameras 428, 424, and 426 can be operated at different NIR frequencies and as seen in FIG. 4B, are positioned a different angles A, B, and C, respectively, with respect to veneer first surface 432. In one embodiment, angle A is 45 degrees, angle B is 90 degrees, and angle C is 135 degrees. As noted, the arrangement shown in FIG. 3B allows different types and levels of irregularities to be detected. In addition, using two or more NIR cameras, such as NIR cameras 428, 424, and 426, that are positioned a different angles means that different irregularities will have surfaces perpendicular to the camera lens and therefore will yield a 3-D-like effect when a composite NIR image is constructed.

[0232] As noted above, in some embodiments, two or more illumination sources, such as illumination source 422, are utilized, that are positioned a different angles with respect to veneer first surface 432. This allows different types and levels of irregularities to be detected. In addition, using two or more two or more illumination sources, such as illumination source 422, that are positioned at different angles means that different irregularities will have surfaces perpendicular to the camera lens and therefore will yield a 3-D effect when a composite NIR image is constructed.

[0233] Consequently, in some embodiments, in an arrangement similar to FIG. 4B, a first illumination source can positioned such that line from the first illumination source is at an angle “A” with respect to veneer first surface, a second illumination source can positioned such that line from the second illumination source is at an angle “B” with respect to veneer first surface, and a third illumination source can positioned such that line from the third illumination source is at an angle “C” with respect to veneer first surface. As discussed above, in some embodiments, angles A, B, and C, respectively, with respect to veneer first surface are all different and, in one very specific embodiment, angle A is 45 degrees, angle B is 90 degrees, and angle C is 135 degrees.

[0234] In addition, as discussed in the disclosed related applications, in some embodiments, visual cameras may be combined to further refine the NIR image based on physical features such as knots that impact veneer ribbon peel quality, or thermal cameras that show temperature variations in the material temperature that impacts veneer ribbon peel quality peel quality.

[0235] Returning to FIG. 4A, using the concepts discussed above, the mapping data 412 of surface irregularity to greyscale mapping database 410 is obtained through one or more empirical and/or manual processes.

[0236] For instance, in one embodiment, sample full veneer sheet, veneer strip, and/or partial veneer sheets that have been identified and associated with one or more production parameter values can be passed through NIR analysis station 420 and known production parameter NIR images can be obtained for numerous sample full veneer sheets, veneer strips, and/or partial veneer sheets determined to be produced by known production parameters.

[0237] FIGS. 4C to 4H are illustrative examples of NIR images of surfaces of veneer produced under various optimal and non-optimal production parameters. In the specific examples of FIGS. 4C to 4H the NIR image illustrations of 4C, 4D, 4E, 4F, 4G and 4H, correlate to the magnified visual image illustrations of FIGS. 2A, 2B, 2C, 2D, 2E and 2F, respectively.

[0238] Consequently, FIG. 4C is a representation of an NIR image of a veneer surface that was produced from an optimally preconditioned conditioned log, FIG. 4D is a representation of an NIR image of a veneer surface that was produced from an over preconditioned log, FIG. 4E is a representation of an NIR image of a veneer surface that was produced from an under preconditioned log, FIG. 4F is a representation of an NIR image of a veneer surface that was produced under conditions where the cutting knife edge was irregular, nicked, or otherwise damaged, FIG. 4G is a representation of an NIR image of a veneer surface that was produced under conditions where the cutting knife edge was not held against the surface of the preconditioned log with a steady pressure, and FIG. 4H is a representation of an NIR image of a veneer surface that was produced under conditions where the cutting knife was dull.

[0239] Therefore, in the specific illustrative examples of FIGS. 2A and 4C, sample veneer ribbons, full veneer sheets, veneer strips, and/or partial veneer sheets determined empirically to be produced from optimally preconditioned wood sources, such as shown in FIG. 2A, can be passed through NIR analysis station 420 to generate known optimally preconditioned wood NIR images of surface 405 of veneer 403, as shown in FIG. 4C.

[0240] Similarly, in the specific illustrative examples of FIGS. 2B and 4D, sample veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets determined empirically to be produced from over preconditioned wood sources, such as shown in FIG. 2B, can be passed through NIR analysis station 420 to generate known over preconditioned wood NIR images of surface 415 of veneer 413, as shown in FIG. 4D.

[0241] Similarly, in the specific illustrative examples of FIGS. 2C and 4E, sample veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets determined empirically to be produced from under preconditioned wood sources, such as shown in FIG. 2C, can be passed through NIR analysis station 420 to generate known under preconditioned wood NIR images of surface 423 of veneer 421, as shown in FIG. 4E.

[0242] Likewise, in the specific illustrative examples of FIGS. 2D and 4F, sample veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets determined empirically to be produced under conditions where the cutting knife edge was irregular, nicked, or otherwise damaged, such as shown in FIG. 2D, can be passed through NIR analysis station 420 to generate known irregular cutting knife edge NIR images of surface 435 of veneer 433, as shown in FIG. 4F.

[0243] Likewise, in the specific illustrative examples of FIGS. 2E and 4G, sample veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets determined empirically to be produced under conditions where the cutting knife edge was not held against the surface of the preconditioned log with a steady pressure, such as shown in FIG. 2E, can be passed through NIR analysis station 420 to generate known irregular cutting knife pressure NIR images of surface 445 of veneer 443, as shown in FIG. 4G.

[0244] Similarly, in the specific illustrative examples of FIGS. 2F and 4H, sample veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets determined empirically to be produced under conditions where the cutting knife edge was dull, such as shown in FIG. 2F, can be passed through NIR analysis station 420 to generate known dull cutting knife NIR images of surface 455 of veneer 453, as shown in FIG. 4H.

[0245] This process is continued for multiple levels and types of surface irregularities and greyscale data for each irregularity increment is determined and correlated to the respective surface irregularities increment. In this way, mapping data 412 mapping each specific surface irregularities to specific greyscale values is generated for veneer ribbons, full veneer sheets, veneer strips, and/or partial veneer sheets. The process can then be repeated for different full veneer sheets, veneer strips, and/or partial veneer sheets, different types of wood, and under varying parameters and conditions. Consequently, the specific examples discussed herein are but illustrative examples and do not limit the scope of the invention as set forth in the claims below.

[0246] Returning the FIG. 4A, computing system 452 also includes physical memory 460. In one embodiment, the physical memory 460 includes NIR image data 462 representing one or more NIR images of the illuminated veneer first surface 432 of the veneer 430 captured using NIR camera 424.

[0247] As seen in FIG. 4A, in one embodiment, computing system 452 includes one or more processors 470 for processing the NIR image data representing one or more NIR images of the illuminated veneer first surface 432 of the veneer 430 to generate NIR greyscale image data 464 indicating different irregularity levels in the illuminated veneer first surface 432 of the veneer 430.

[0248] In one embodiment, processor 470 processes the NIR greyscale image data 464 using the mapping data 412 from surface irregularity to greyscale mapping database 410 to identify irregularity levels for the veneer first surface 432 of the veneer 430.

[0249] As seen in FIG. 4A, in one embodiment, computing system 452 includes a grade assignment module 480 for assigning a grade to the veneer 430 based on the identified irregularity levels for the veneer first surface 432. As seen in FIG. 4A, grade assignment module 480 includes surface irregularity analysis module 474 which, along with processor 470, processes the NIR greyscale image data 464 using the mapping data 412 from surface irregularity to greyscale mapping database 410 data to identify irregularity levels for the veneer first surface 432 of the veneer 430. As a result of the processing by surface irregularity analysis module 474 and processor 470, grade assignment data 482 is generated.

[0250] As seen in FIG. 4A, in one embodiment, grade assignment data 482 is provided to action selection and activation module 490 which selects an appropriate action of the actions represented in available actions data 492 based, at least in part on the grade indicated by grade assignment data 482. As seen in FIG. 4A, in one embodiment, the determined appropriate action is represented by selected action data 494.

[0251] As seen in FIG. 4A, in one embodiment, selected action data 494 is forwarded to an action activation module, such as selected action implementation module 496, in production floor environment 401 to initialize one or more actions with respect to the veneer 430 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 by action selection and activation module 490. These actions can include assigning the veneer 430 to a specific veneer stack associated with the grade assigned to the veneer 430.

[0252] As discussed in more detail below, in some embodiments, the selected action indicated by selected action data 494 is to add veneer 430 to a specific veneer stack based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430. In these embodiments, grade assignment data 482 is provided to action selection and activation module 490 which, in turn, forwards grade assignment data 482 to selected action implementation module 496. In one embodiment, selected action implementation module 496 then forwards grade assignment data 482 to a stacking system such as any stacking system discussed herein. As discussed in more detail below, in these embodiments, the veneer 430 is then added to a specific veneer stack based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430.

[0253] In other embodiments, the one or more actions that can be taken represented in available actions data 492 can also include, but are not limited to: sorting veneer 430 into a bin or location based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; restricting the use of the veneer 430 based on the grade represented by grade assignment data 482 assigned to veneer 430; rejecting the veneer 430 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; sending the veneer 430 back for further processing based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; adjusting one or more processing parameters of a production line based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and one or more similarly graded similar full veneer sheet, veneer strip, and/or partial veneer sheets; adjusting one or more preconditioning parameters on a production line based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and/or one or more similarly graded full veneer sheet, veneer strip, and/or partial veneer sheets; adjusting one or more veneer cutting parameters on a production line based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and/or one or more similarly graded full veneer sheet, veneer strip, and/or partial veneer sheets; and selecting a type and amount of glue used on a production line in production floor environment 401 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and/or the grades assigned other full veneer sheet, veneer strip, and/or partial veneer sheets.

[0254] Those of skill in the art will ready recognize that the specific illustrative examples of one embodiment of a production floor environment 401 and components shown in FIGS. 4A and 4B are but specific examples of numerous possible production environments and arrangement of physical components. Consequently, the specific illustrative example of embodiments of a production floor environment 401 and components shown in FIGS. 4A and 4B is not intended to limit the scope of the invention as set forth in the claims below.

[0255] Likewise, those of skill in the art will ready recognize that the specific illustrative examples of one embodiment of FIGS. 2A through 2F and corresponding FIGS. 4C through 4H are but specific examples of numerous possible images. Consequently, the specific illustrative examples of one embodiment shown in FIGS. 2A through 2F and corresponding FIGS. 4C through 4H are not intended to limit the scope of the invention as set forth in the claims below.

[0256] As a specific illustrative example of potential variations, in various embodiments, the NIR analysis station 420 can include one or more illumination sources 422 positioned to illuminate two or more surfaces of the veneer and one or more NIR cameras 424 positioned to capture one or more NIR images of the two or more illuminated surfaces of the veneer.

[0257] As a further specific illustrative example of variations possible, additional input data can be considered such as current ambient temperature and humidity. The combination of these parameters can be analyzed by an Artificial Intelligence/Machine Learning (AI/ML) algorithm to further refine the production parameters for overall process efficiency.

[0258] These and numerous other variations are possible and contemplated by the inventors to be within the scope of the invention as set forth in the claims below.

[0259] FIG. 5 is flow chart of a process 500 for detecting surface irregularity levels in veneer using NIR technology in accordance with one embodiment.

[0260] As seen in FIG. 5, process 500 begins at BEGIN operation 502 and then process proceeds to operation 504. In one embodiment, at operation 504 a surface irregularity level to greyscale mapping database is generated such as any database discussed above with respect to FIGS. 3A, FIGS. 2A through 2F and corresponding FIGS. 4C through 4H. In one embodiment, the surface irregularity level to greyscale mapping database contains mapping data that maps surface irregularities level to Near InfraRed (NIR) image greyscale values for one or more full veneer sheets, veneer strips, and/or partial veneer sheets.

[0261] Once a surface irregularity level to greyscale mapping database is generated at operation 504, process flow proceeds to operation 506. At operation 506, an NIR analysis station is provided. In one embodiment, the NIR analysis station is substantially similar to any NIR analysis station discussed above with respect to FIGS. 4A and 4B. As discussed above, in one embodiment, the NIR analysis station includes one or more sources of illumination positioned to illuminate a surface of wood product such as veneer and one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the veneer.

[0262] Once an NIR analysis station is provided at operation 506, process flow proceeds to operation 508. In one embodiment, at operation 508, a wood product such as veneer to be analyzed is positioned in the NIR analysis station of operation 506 such that a first surface of the wood product such as veneer to be analyzed is illuminated by the one or more illumination sources using any of the methods and systems discussed above with respect to FIGS. 4A and 4B.

[0263] Once the wood product such as veneer to be analyzed is positioned in the NIR analysis station at 508, process flow proceeds to operation 510. In one embodiment, at operation 510 the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the wood product such as veneer using any of the methods and systems discussed above with respect to FIGS. 4A and 4B.

[0264] Once the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the wood product such as veneer at operation 510, process flow proceeds to operation 512.

[0265] In one embodiment, at operation 512, the one or more NIR images of the illuminated first surface of the wood product such as veneer of operation 510 are processed using any of the methods and systems discussed above with respect to FIGS. 4A and 4B, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H, to generate NIR greyscale images indicating irregularities in the illuminated first surface of the wood product such as veneer.

[0266] Once the one or more NIR images of the illuminated first surface of the wood product such as veneer are processed to generate NIR greyscale images indicating different irregularities in the illuminated first surface of the wood product such as veneer at operation 512, process flow proceeds to operation 514.

[0267] In one embodiment, at operation 514, the NIR greyscale images are processed using the surface irregularity level to greyscale mapping database to identify irregularity levels for the first surface of the wood product such as veneer by any of the methods and systems discussed above with respect to FIGS. 4A and 4B, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H.

[0268] Once the NIR greyscale images are processed using the surface irregularity level to greyscale mapping database to identify irregularity levels for the first surface of the wood product such as veneer at operation 514, process flow proceeds operation 516.

[0269] In one embodiment, at operation 516 a grade is assigned to the wood product such as veneer based on the identified irregularity levels for the wood product such as first surface of the veneer using any of the methods and systems discussed above with respect to FIGS. 4A and 4B, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H.

[0270] Once a grade is assigned to the wood product such as veneer based on the identified irregularity levels for the first surface of the wood product such as veneer at operation 516, process flow proceeds to operation 518. In one embodiment, at operation 518, based at least in part, on the grade assigned to the wood product such as veneer, one or more actions are taken with respect to the wood product such as veneer including, but not limited to, assigning the veneer to a specific veneer stack associated with the grade assigned to the veneer and/or any of the actions discussed above with respect to the methods and systems discussed above with respect to FIGS. 4A and 4B.

[0271] As discussed in more detail below, in some embodiments, the selected action of operation 518 is to add the veneer to a specific veneer stack based, at least in part, on the grade assigned to the veneer. As discussed in more detail below, in some embodiments, the selected action is to add the veneer to a specific veneer stack based, at least in part, on the grade assigned to the veneer. In these embodiments, grade assignment data is provided to and action selection and activation module which, in turn, forwards grade assignment data to a selected action implementation module. In one embodiment, the selected action implementation module then forwards the grade assignment data to a stacking system such as any stacking system discussed herein. As discussed in more detail below, in these embodiments, the veneer is then added to a specific veneer stack based, at least in part, on the grade assigned to the veneer.

[0272] Once one or more actions with respect to the wood product such as veneer at operation 518, process flow proceeds to END operation 524 where process 500 is exited to await new samples and/or data.

[0273] FIG. 6 is simplified block diagram of one embodiment of a NIR analysis system 600 for detecting surface irregularity levels in veneer using NIR technology and machine learning methods in accordance with one embodiment.

[0274] In one embodiment, system 600, like NIR analysis system 400 of FIGS. 4A and 4B, includes production floor environment 401 and a computing environment 450. As discussed in more detail below, in one embodiment, NIR analysis system 600 is part of a veneer analysis system.

[0275] As seen in FIG. 6, like NIR analysis system 400 of FIGS. 4A and 4B, production floor environment 401 includes NIR analysis station 420 and selected action implementation module 496. As seen in FIG. 6, NIR analysis station 420 includes one or more illumination sources, such as illumination source 422, positioned to illuminate a veneer first surface 432 of veneer 430. In various embodiments, the one or more sources of illumination, such as illumination source 422, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 422, can include, but are not limited to, halogen or halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0276] As seen in FIG. 6, NIR analysis station 420 also includes one or more NIR cameras, such as NIR camera 424, positioned to capture NIR image data 462 representing one or more NIR images of the illuminated veneer first surface 432 of the veneer 430. In one embodiment, one or more NIR cameras, such as NIR camera 424, are adjustably positioned and adjustably focused to capture one or more NIR images of the illuminated veneer first surface 432 of the veneer 430.

[0277] As seen in FIG. 6, the veneer 430 to be analyzed in the NIR analysis station 420 is positioned in NIR analysis station 420. In various embodiments, the veneer 430 can be any veneer as discussed herein, and/or as known in the art at the time of filing, and/or as becomes known after the time of filing. In one embodiment, the veneer 430 to be analyzed is a veneer sheet.

[0278] In one embodiment, the veneer 430 to be analyzed is positioned such that the veneer first surface 432 of the veneer 430 to be analyzed is illuminated by the illumination source 422 and is within view and focus of NIR camera 424. In one embodiment, the veneer 430 is positioned in the NIR analysis station 420 by passing the veneer 430 through the NIR analysis station 420 on a conveyor system (not shown).

[0279] As seen in FIG. 6, like NIR analysis system 400 of FIGS. 4A and 4B, computing environment 450 includes computing system 452. However, unlike NIR analysis system 400 of FIGS. 4A and 4B, in one embodiment, computing system 452 of system 600 does not include surface irregularity to greyscale mapping database 410 but instead includes surface irregularity prediction module 610.

[0280] In one embodiment, surface irregularity prediction module 610 includes one or more trained Machine Learning (ML) based surface irregularity prediction models, such as Machine Learning (ML) based surface irregularity prediction model 612. In various embodiments the one or more trained machine learning based surface irregularity prediction models, such as machine learning based surface irregularity prediction model 612, are trained using NIR image data for one or more full veneer sheet, veneer strip, and/or partial veneer sheets and corresponding determined irregularity levels for the one or more full veneer sheet, veneer strip, and/or partial veneer sheets.

[0281] Various types of machine learning based models are well known in the art. Consequently, the one or more trained machine learning based surface irregularity prediction models, such as machine learning based surface irregularity prediction model 612, can be any machine learning based model type or use any machine learning based algorithm, as discussed herein, and/or as known in the art at the time of filing, and/or as becomes known or available after the time of filing.

[0282] Specific illustrative examples of machine learning based model types and machine learning based algorithms that can be used for, or with, the one or more trained machine learning based surface irregularity prediction models of surface irregularity prediction module 610, such as machine learning based surface irregularity prediction model 612, include, but are not limited to: supervised machine learning-based models; semi-supervised machine learning-based models; unsupervised machine learning-based models; classification machine learning-based models; logistical regression machine learning-based models; neural network machine learning-based models; and deep learning machine learning-based models.

[0283] In various embodiments, and largely depending on the machine-learning based models used, the NIR image data for one or more full veneer sheet, veneer strip, and/or partial veneer sheets, including in some cases various environmental and production parameters, and corresponding determined irregularity levels for the one or more full veneer sheet, veneer strip, and/or partial veneer sheets can be processed using various methods known in the machine learning arts to identify elements and vectorize the NIR image data and/or corresponding determined irregularity levels data. As a specific illustrative example, in a case where the machine learning based model is a supervised model, the NIR image data can be analyzed and processed into elements found to be indicative of veneer irregularity levels, product failures, and product performance. Then these elements are used to create vectors in multidimensional space which are, in turn, used as input data for one or more machine learning models. The correlated determined irregularity levels, product failures, and product performance data for each NIR image data vector is then used as a label for the resulting vector. This process is repeated for multiple, often millions, of correlated pairs of NIR image data vector and determined irregularity levels, product failures, and product performance data with the result being one or more trained machine learning based surface irregularity prediction models.

[0284] Then when new NIR image data is obtained, this new NIR image data is also vectorized and the new NIR image vector data is provided as input data to the one or more trained machine learning based surface irregularity prediction models. The new NIR image vector data is then processed to find a distance between the new NIR image vector and previously labeled NIR image vectors, whose associated irregularity level data is known. Based on a calculated distance between the new NIR image vector data and the previously labeled NIR image vector data, a probability that the new NIR image vector data correlates to an irregularity level, product failure, or product performance associated with the previously labeled NIR image vector data can be calculated. This results in a probability score for the veneer being analyzed.

[0285] Those of skill in the art will readily recognize that there are many different types of machine learning based models known in the art. Consequently, the specific illustrative example of a specific supervised machine learning based model discussed above is not limiting.

[0286] As seen in FIG. 6, computing system 452 also includes physical memory 460. In one embodiment, the physical memory 460 includes NIR image data 462 representing one or more NIR images of the illuminated veneer first surface 432 of the veneer 430 captured using NIR camera 424.

[0287] As seen in FIG. 6, in one embodiment, computing system 452 includes one or more processors, such as processor 470, for generating the NIR image data 462 representing one or more NIR images of the illuminated veneer first surface 432 of the veneer 430 from NIR camera 424.

[0288] In one embodiment, NIR image data 462 is provided to surface irregularity prediction module 610 where it is processed/vectorized and provided to machine learning based irregularity level prediction model 612.

[0289] Machine learning based irregularity level prediction model 612 then processes the vectorized NIR image data 462 as discussed above and generates irregularity prediction data 614 for the veneer 430.

[0290] As seen in FIG. 6, irregularity prediction data 614 for the veneer 430 is then provided to grade assignment module 480. As discussed above, grade assignment module 480 then assigns a grade to the veneer 430 based on irregularity prediction data 614 for the veneer 430.

[0291] As seen in FIG. 6, grade assignment module 480 includes surface irregularity analysis module 474 which, along with processor 470, processes irregularity prediction data 614 for the veneer 430 and generates grade assignment data 482 based on this processing

[0292] As seen in FIG. 6, in one embodiment, grade assignment data 482 is provided to action selection and activation module 490 which selects an appropriate action of the actions represented in available actions data 492 based, at least in part on the grade indicated by grade assignment data 482. As seen in FIG. 6, in one embodiment, the determined appropriate action is represented by selected action data 494.

[0293] As seen in FIG. 6, in one embodiment, selected action data 494 is forwarded to an action activation module, such as selected action implementation module 496 in production floor environment 401, to initialize one or more actions with respect to the veneer 430 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 by action selection and activation module 490 including, but not limited to, assigning the veneer 430 to a specific veneer stack associated with the grade assigned to the veneer.

[0294] As discussed in more detail below, in some embodiments, the selected action indicated by selected action data 494 is to add veneer 430 to a specific veneer stack based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430. In these embodiments, grade assignment data 482 is provided to action selection and activation module 490 which, in turn, forwards grade assignment data 482 to selected action implementation module 496. In one embodiment, selected action implementation module 496 then forwards grade assignment data 482 to a stacking system such as any stacking system discussed herein. As discussed in more detail below, in these embodiments, the veneer 430 is then added to a specific veneer stack based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430.

[0295] In one embodiment, one or more actions that can be taken represented in available actions data 492 can also include, but are not limited to: sorting veneer 430 into a bin or location based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; restricting the use of the veneer 430 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; rejecting the veneer 430 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; sending the veneer 430 back for further processing based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430; adjusting one or more processing parameters of a production line based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and one or more similarly graded similar full veneer sheet, veneer strip, and/or partial veneer sheets; adjusting one or more preconditioning parameters on a production line based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and/or one or more similarly graded full veneer sheet, veneer strip, and/or partial veneer sheets; adjusting one or more veneer cutting parameters on a production line based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and/or one or more similarly graded full veneer sheet, veneer strip, and/or partial veneer sheets; and selecting a type and amount of glue used on a production line in production floor environment 401 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and/or the grades assigned other full veneer sheet, veneer strip, and/or partial veneer sheets.

[0296] Those of skill in the art will ready recognize that the specific illustrative example of one embodiment of FIG. 6 is but one example of numerous possible production environments and arrangement of components. Consequently, the specific illustrative example of one embodiment shown in FIG. 6 is not intended to limit the scope of the invention as set forth in the claims below.

[0297] As a specific illustrative example of possible variations, in some embodiments, the NIR analysis station 420 can include one or more illumination sources 422 positioned to illuminate two or more surfaces of veneer and one or more NIR cameras 424 positioned to capture one or more NIR images of the two or more illuminated surfaces of the veneer.

[0298] FIG. 7 is flow chart of a process 700 for detecting surface irregularity levels in wood product such as a veneer using NIR technology and machine learning methods in accordance with one embodiment.

[0299] As seen in FIG. 7, process 700 begins at BEGIN operation 702 and then process proceeds to operation 704. In one embodiment, at operation 704 one or more machine learning based surface irregularity prediction models are trained using NIR image data for one or more full veneer sheet, veneer strip, and/or partial veneer sheets and determined corresponding irregularity levels and/or failures for the one or more full veneer sheets, veneer strips, and/or partial veneer sheets by any of the systems or methods discussed above with respect to FIG. 6.

[0300] In one embodiment, once one or more machine learning based surface irregularity prediction models are trained using NIR image data for one or more full veneer sheet, veneer strip, and/or partial veneer sheets and determined corresponding irregularity levels for the one or more full veneer sheet, veneer strip, and/or partial veneer sheets at operation 704, process flow proceeds to operation 706.

[0301] At operation 706, an NIR analysis station is provided. In one embodiment, the NIR analysis station is substantially similar to any NIR analysis station discussed above with respect to FIGS. 4A, 4B, and 6, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H. As discussed above, in one embodiment, the NIR analysis station includes one or more sources of illumination positioned to illuminate a surface of veneer and one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the veneer.

[0302] Once an NIR analysis station is provided at operation 706, process flow proceeds to operation 708. In one embodiment, at operation 708, veneer to be analyzed is positioned in the NIR analysis station of operation 706 such that a first surface of the veneer to be analyzed is illuminated by the one or more illumination sources using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, and 6, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H.

[0303] Once the veneer to be analyzed is positioned in the NIR analysis station at 708, process flow proceeds to operation 710. In one embodiment, at operation 710 the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the veneer using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, and 6, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H.

[0304] Once the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the veneer at operation 710, process flow proceeds to operation 712.

[0305] In one embodiment, at operation 712, the one or more NIR images of the illuminated first surface of the veneer of operation 710 are processed, using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, and 6, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H, to generate NIR image data such as any NIR image data discussed above with respect to FIGS. 4A, 4B, and 6, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H.

[0306] Once the one or more NIR images of the illuminated first surface of the veneer are processed to generate NIR image data at operation 712, process flow proceeds to operation 714.

[0307] In one embodiment, at operation 714 the NIR image data for the illuminated first surface of the veneer of operation 712 is processed and provided to the one or more trained machine learning based surface irregularity prediction models using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, and 6, FIGS. 2A through 2F, and corresponding FIGS. 4C through 4H.

[0308] Once the NIR image data for the illuminated first surface of the veneer is processed and provided to the one or more trained machine learning based surface irregularity prediction models at operation 714, process flow proceeds to process 716.

[0309] In one embodiment, at operation 716 the one or more trained machine learning based surface irregularity prediction models generate irregularity prediction data for the veneer using any of the methods and systems discussed above with respect to FIG. 6.

[0310] Once irregularity prediction data for the veneer is obtained from the one or more trained machine learning based surface irregularity prediction models at operation 716, process flow proceeds to operation 718.

[0311] In one embodiment, at operation 718, a grade is assigned to the veneer based on the surface irregularity prediction data for the veneer at operation 716 using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, and 6.

[0312] Once a grade is assigned to the veneer based on the surface irregularity prediction data for the veneer at operation 718, process flow proceeds to operation 720. In one embodiment, at operation 720, based, at least in part, on the grade assigned to the veneer, one or more actions are taken with respect to the veneer including any of the actions discussed above with respect to the methods and systems discussed above with respect to FIGS. 4A, 4B, and 6.

[0313] As discussed in more detail below, in some embodiments, the selected action of operation 720 is to add the veneer to a specific veneer stack based, at least in part, on the grade assigned to the veneer. As discussed in more detail below, in some embodiments, the selected action is to add the veneer to a specific veneer stack based, at least in part, on the grade assigned to the veneer. In these embodiments, grade assignment data is provided to and action selection and activation module which, in turn, forwards grade assignment data to a selected action implementation module. In one embodiment, the selected action implementation module then forwards the grade assignment data to a stacking system such as any stacking system discussed herein. As discussed in more detail below, in these embodiments, the veneer is then added to a specific veneer stack based, at least in part, on the grade assigned to the veneer.

[0314] Once one or more actions with respect to the veneer at operation 720, process flow proceeds to END operation 734 where process 700 is exited to await new samples and/or data.

[0315] FIG. 8 is simplified block diagram of one embodiment of an NIR analysis system 800 for adjusting a preconditioning process of wood sources used to produce full veneer sheet, veneer strip, and/or partial veneer sheets based on NIR imagery of a first surface of the full veneer sheet, veneer strip, and/or partial veneer sheets in accordance with one embodiment.

[0316] As with NIR analysis system 400 discussed above with respect to FIG. 3A, in one embodiment, system 800 includes production floor environment 401 and computing environment 450. As seen in FIG. 8, production floor environment 401 includes NIR analysis station 420. As seen in FIG. 8, NIR analysis station 420 includes one or more illumination sources, such as illumination source 422, positioned to illuminate a surface of veneer ribbon 830. In various embodiments, the one or more illumination sources, such as illumination source 422, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 422, can include, but are not limited to, halogen, halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0317] As with NIR analysis system 400 discussed above with respect to FIG. 3A, in FIG. 8, NIR analysis station 420 also includes one or more NIR cameras, such as NIR camera 424, positioned to capture NIR image data 462 representing one or more NIR images of the illuminated veneer ribbon 830. In one embodiment, the one or more NIR cameras, such as NIR camera 424, are adjustably positioned and adjustably focused to capture any desired one or more NIR images of the illuminated surface of the veneer ribbon 830.

[0318] As seen in FIG. 8, and as discussed below the veneer ribbon 830 to be analyzed in the NIR analysis station 420 is positioned in NIR analysis station 420. In the specific illustrative example of FIG. 8, the veneer ribbon 830 is a veneer ribbon 830 rotary cut from preconditioned wood source 801, such as a preconditioned peeler log.

[0319] In one embodiment, the veneer ribbon 830 to be analyzed is positioned such that a veneer ribbon first surface 832 of the veneer ribbon 830 to be analyzed is illuminated by the illumination source 422 and the sample portion or entire veneer ribbon first surface 832 is within view and focus of NIR camera 424. In one embodiment, the veneer ribbon 830 is positioned in the NIR analysis station 420 by passing the veneer ribbon 830 through the NIR analysis station 420 on a conveyor system.

[0320] In various embodiments, the one or more NIR cameras, such as NIR camera 424, can be of any resolution desired. As noted above, when the one or more NIR cameras, such as NIR camera 424, are used to scan the veneer ribbon first surface 832 of a veneer ribbon 830 for irregularities and create an NIR image data 462 of the veneer ribbon first surface 832, essentially each pixel generated by NIR camera 424 is a sample point. Consequently, the resolution and accuracy of the surface irregularity detection process is only limited by the number of pixels the NIR camera 424 has covering the field of view, e.g., the entire veneer ribbon first surface 832 of veneer ribbon 830. Consequently, in the case where NIR camera 424 is a 1.3 mega pixel camera, there are essentially 1,400,000 individual measurement points on the veneer ribbon first surface 832. In addition, NIR wavelengths are in the range of 750 nanometers (nm) to 4500 nm which are much smaller that the visible wavelengths of 480 to 740 nm. Consequently, using NIR cameras, such as NIR camera 424, results in resolutions and accuracy that simply cannot be achieved using traditional surface magnified visual image methods.

[0321] Therefore, using NIR cameras, such as NIR camera 424, system 800 is capable of detecting irregularities in a wide range of samples sizes ranging from of a traditional 2″×2″ square, to a full 4′×8′ sheet or panel surface, and, by using a series of NIR images spliced together, up to an 80′-120′ ribbon of material. This, in turn, allows the disclosed embodiments to be implemented without significantly slowing down the production process or increasing the cost of the finished veneer.

[0322] As seen in FIG. 8, computing environment 450 includes computing system 452. As seen in FIG. 8, in one embodiment, computing system 452 includes surface irregularity to greyscale mapping database 410 containing mapping data 412 that maps surface irregularities to Near InfraRed (NIR) image greyscale values for veneer.

[0323] As discussed in some detail above with respect to FIG. 4A, using NIR images, extremely granular differences in irregularity levels can be detected. In general, locations with different levels of irregularities absorb/reflect different amounts of NIR radiation at specific frequencies. In operation, when NIR radiation of a given frequency is applied to a veneer ribbon first surface 832 of veneer ribbon 830, more NIR energy is reflected from surfaces that are perpendicular the NIR camera lens. Consequently, at locations having irregularities such that the surfaces are not perpendicular the NIR camera lens will appear darker, i.e., have a greater greyscale value.

[0324] When the NIR camera 424 takes an image of the veneer ribbon first surface 832, the NIR camera 424 picks up the NIR energy reflected off veneer ribbon first surface 832 at approximately 90 degrees. Consequently, when the NIR camera 424 takes an image of the veneer ribbon first surface 832, the areas of irregularities, which scatter more NIR energy at angles other than 90 degrees and therefore reflect less NIR energy, appear darker than dry areas. In addition, the higher or more significant the irregularities that are present, the darker the area appears because less NIR energy is reflected to be captured by the NIR camera 424.

[0325] Using this fact, NIR image data 462 captured by the NIR camera 424 can be processed into NIR greyscale image data 464. Greyscale images can be of varying resolution, or bit, types. A 16-bit integer grayscale image provides 65535 available tonal steps from 0 (black) to 65535 (white). A 32-bit integer grayscale image theoretically will provide 4,294,967,295 tonal steps from 0 (black) to 4294967295 (white). Converting an NIR image based on these number of greyscale tonal steps results in a margin of error of significantly less than 0.1%.

[0326] In some embodiments, two or more NIR cameras are utilized, such as NIR camera 424, that are operated at different NIR frequencies and/or that are positioned a different angles with respect to veneer ribbon first surface 832. This allows different types and levels of irregularities to be detected. In addition, using two or more NIR cameras, such as NIR camera 424, that are positioned at different angles means that different irregularities will have surfaces perpendicular to the camera lens and therefore will yield a 3-D effect when a composite NIR image is constructed. A more detailed discussion of a one example of a multi-NIR camera system is discussed above with respect to FIG. 3B.

[0327] Returning to FIG. 8, and using the concepts discussed above, the mapping data 412 of surface irregularity to greyscale mapping database 410 is obtained through one or more empirical and/or manual processes, as discussed above with respect to FIG. 4A.

[0328] As discussed above, FIGS. 4C to 4H are illustrative examples of NIR images of surfaces of veneer produced under various optimal and non-optimal production parameters. In the specific examples of FIGS. 4C to 4H the NIR image illustrations of 4C, 4D, 4E, 4F, 4G and 4H, correlate to the magnified visual image illustrations of FIGS. 2A, 2B, 2C, 2D, 2E and 2F, respectively.

[0329] Returning the FIG. 8, computing system 452 also includes NIR greyscale image to preconditioning mapping database. In one embodiment, NIR greyscale image to preconditioning mapping database 810 include preconditioning mapping data 812 that maps NIR greyscale images to particular preconditioning parameters and issues based on known data obtained from known condition greyscale images, such as images 4C, 4D, and 4E.

[0330] Computing system 452 also includes physical memory 460. In one embodiment, the physical memory 460 includes NIR image data 462 representing one or more NIR images of the illuminated veneer ribbon first surface 832 of the veneer ribbon 830 captured using NIR camera 424. Physical memory 460 also includes NIR greyscale image data 464. In one embodiment, computing system 452 includes one or more processors 470 for processing the NIR image data representing one or more NIR images of the illuminated veneer ribbon first surface 832 of the veneer ribbon 830 to generate NIR greyscale image data 464 indicating different irregularity levels in the illuminated veneer ribbon first surface 832 of the veneer ribbon 830.

[0331] In one embodiment, processor 470 processes the NIR greyscale image data 464 using the mapping data 412 from surface irregularity to greyscale mapping database 410 to identify irregularity levels for the veneer ribbon first surface 832 of the veneer ribbon 830.

[0332] As seen in FIG. 8, in one embodiment, computing system 452 includes a preconditioning level analysis module 874 which analyzes preconditioning mapping data 812 and NIR greyscale image data 464 to determine a preconditioning parameter level represented by preconditioning level data 882. In various embodiments, preconditioning level data 882 determines which, if any, preconditioning parameters must be readjusted to adjust the preconditioning levels of subsequent wood sources.

[0333] Available preconditioning parameter adjustments data 892 includes data representing the available precondition adjustments such as, adjusting of chemical composition of the caustic water mix by adding or subtracting chemical or changing chemical; adjusting the temperature of the caustic water mix; or adjusting the soak time for preconditioned wood source 801, such as logs, in the vats of caustic water mix. The determined preconditioning parameter adjustment is then represented by preconditioning level data 882.

[0334] In some embodiments, preconditioning level analysis module 874 includes one or more machine learning based models such as any machine learning based models discussed herein, and/or as known in the art at the time of filing, and/or as become known/available after the time of filing.

[0335] For instance, based on the analysis of NIR greyscale image data 464 and preconditioning mapping data 812, preconditioning level analysis module 874 may determine a probability that the chemical used, or amount of chemical used in the preconditioning vat soak needs to be adjusted. Likewise, based on the analysis of NIR greyscale image data 464 and preconditioning mapping data 812, preconditioning level analysis module 874 may determine that the preconditioning vat soak time needs to be adjusted. Similarly, based on the analysis of NIR greyscale image data 464 and preconditioning mapping data 812, preconditioning level analysis module 874 may determine that the preconditioning temperature needs to be adjusted. In some cases, based on the analysis of NIR greyscale image data 464 and preconditioning mapping data 812, preconditioning level analysis module 874 may determine any combination, or all, of these preconditioning parameters, or other preconditioning parameters, need to be adjusted.

[0336] In various embodiments, the adjustments determined to be necessary by preconditioning level analysis module 874 are then represented by preconditioning level data 882 which is used to adjust the preconditioning parameters for subsequent wood sources. Once generated by preconditioning level analysis module 874, preconditioning level data 882 is provided to preconditioning parameter adjustment activation module 890 which generates selected adjustment data 894.

[0337] In various embodiments, selected adjustment data is then transferred to preconditioning control 897 in preconditioning environment 895 where the adjustments determined to be necessary by preconditioning level analysis module 874 are implemented. These can include one or more of: adjusting of chemical composition of the caustic water mix by adding or subtracting chemical or changing chemical; adjusting the temperature of the caustic water mix; or adjusting the soak time for preconditioned wood source 801, such as logs, in the vats of caustic water mix.

[0338] Using system 800 the preconditioning process so critical to veneer ribbon 830 production is adjusted dynamically using feedback based on actual veneer ribbon, veneer NIR surface image analysis. Consequently, using system 800, finding the best combination of chemical composition of the caustic water mix, temperature of the caustic water mix, and soak time for the logs in the vats of caustic water mix is more accurately determined based on empirical and relative real-time data. As a result, accurate adjustments can be made to minimize wasted product and maximize product value.

[0339] Those of skill in the art will ready recognize that the specific illustrative examples of one embodiment of a production floor environment 401 and components shown in FIG. 8 are but specific examples of numerous possible production environments and arrangement of physical components. Consequently, the specific illustrative example of an embodiment of a production floor environment 401 and components shown in FIGS. 8 is not intended to limit the scope of the invention as set forth in the claims below.

[0340] As a specific illustrative example of potential variations, in various embodiments, the NIR analysis station 420 can include one or more illumination sources 422 positioned to illuminate two or more surfaces of veneer and one or more NIR cameras 424 positioned to capture one or more NIR images of the two or more illuminated surfaces of the veneer ribbon 830.

[0341] As a further specific illustrative example of variations possible, additional input data can be considered such as current ambient temperature and humidity. The combination of these parameters can be analyzed by an AI/ML algorithm to further refine the production parameters for overall process efficiency.

[0342] These and numerous other variations are possible and contemplated by the inventors to be within the scope of the invention as set forth in the claims below.

[0343] FIG. 9 is flow chart of a process 900 for adjusting a preconditioning process of wood sources used to produce veneer based on a level of irregularity of a first surface of the veneer in accordance with one embodiment.

[0344] As seen in FIG. 9, process 900 begins at BEGIN operation 902 and then process proceeds to operation 904. In one embodiment, at operation 904 a surface irregularity level to greyscale mapping database is generated such as any database discussed above with respect to FIG. 3A, FIG. 8, FIGS. 2A through 2C, and corresponding FIGS. 4C through 4H. In one embodiment, the surface irregularity level to greyscale mapping database contains mapping data that maps surface irregularities to Near InfraRed (NIR) image greyscale values for one or more veneer.

[0345] Once a surface irregularity level to greyscale mapping database is generated at operation 904, process flow proceeds to operation 905. In one embodiment, at operation 905 an NIR greyscale image to preconditioning level mapping database is generated using any of the methods and systems discussed above with respect to FIG. 8.

[0346] Once an NIR greyscale image to preconditioning level mapping database is generated at operation 905, process flow proceeds to operation 906. At operation 906, an NIR analysis station is provided. In one embodiment, the NIR analysis station is substantially similar to any NIR analysis station discussed above with respect to FIGS. 4A, 4B, and 8. As discussed above, in one embodiment, the NIR analysis station includes one or more sources of illumination positioned to illuminate a surface of the veneer and one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the veneer.

[0347] Once an NIR analysis station is provided at operation 906, process flow proceeds to operation 908. In one embodiment, at operation 908, the veneer to be analyzed is positioned in the NIR analysis station of operation 906 such that a first surface of the veneer to be analyzed is illuminated by the one or more illumination sources using any of the methods and systems discussed above with respect to FIG. 4A, FIG. 8, FIGS. 2A through 2C, and corresponding FIGS. 4C through 4H.

[0348] Once the veneer to be analyzed is positioned in the NIR analysis station at 908, process flow proceeds to operation 910. In one embodiment, at operation 910 the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the veneer using any of the methods and systems discussed above with respect to FIGS. 3A, 3B and 8.

[0349] Once the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the veneer at operation 910, process flow proceeds to operation 912.

[0350] In one embodiment, at operation 912, the one or more NIR images of the illuminated first surface of the veneer of operation 910 are processed using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, FIG. 8, FIGS. 2A through 2C, and corresponding FIGS. 4C through 4H, to generate NIR greyscale images indicating different irregularity levels in the illuminated first surface of the veneer.

[0351] Once the one or more NIR images of the illuminated first surface of the veneer are processed to generate NIR greyscale images indicating different irregularity levels in the illuminated first surface of the veneer at operation 912, process flow proceeds to operation 913.

[0352] In one embodiment, at operation 913, the NIR greyscale images are processed using NIR greyscale image to preconditioning level mapping database to determine a preconditioning level and preconditioning parameter adjustments using any of the methods and systems discussed above with respect to FIGS. 4A and 4B, FIG. 8, FIGS. 2A through 2C, and corresponding FIGS. 4C through 4H.

[0353] Once the NIR greyscale images are processed using NIR greyscale image to preconditioning level mapping database to determine a preconditioning level and preconditioning parameter adjustments at operation 913, process flow proceeds to operation 914.

[0354] In one embodiment, at operation 914 any preconditioning parameters that it is determined must be adjusted are adjusted via one or more actions such as any actions discussed above with respect to FIG. 8.

[0355] Once any preconditioning parameters that it is determined must be adjusted are adjusted at operation 914, process flow proceeds to END operation 934 where process 900 is exited to await new samples and/or data.

[0356] FIG. 10 is simplified block diagram of a system 1000 for adjusting processing parameters used to produce a veneer ribbon 1030 from a wood source based on a NIR images of a surface of the veneer ribbon 1030 in accordance with one embodiment.

[0357] As with NIR analysis system 400 discussed above with respect to FIG. 4A, in one embodiment, NIR analysis system 1000 includes production floor environment 401 and computing environment 450. As seen in FIG. 10, production floor environment 401 includes NIR analysis station 420. As seen in FIG. 10, NIR analysis station 420 includes one or more illumination sources, such as illumination source 422, positioned to illuminate a surface of veneer ribbon 1030. In various embodiments, the one or more illumination sources, such as illumination source 422, can include one or more LED light sources. In other embodiments, the one or more illumination sources, such as illumination source 422, can include, but are not limited to, halogen, halogen and tungsten light sources, or any other light sources, as discussed herein, and/or as known in the art at the time of filing, and/or as developed after the time of filing.

[0358] As with NIR analysis system 400 discussed above with respect to FIG. 4A, in FIG. 10, NIR analysis station 420 also includes one or more NIR cameras, such as NIR camera 424, positioned to capture NIR image data 462 representing one or more NIR images of the illuminated surface of the veneer ribbon 1030. In one embodiment, the one or more NIR cameras, such as NIR camera 424, are adjustably positioned and adjustably focused to capture any desired one or more NIR images of the illuminated surface of the veneer ribbon 1030.

[0359] As seen in FIG. 10, and as discussed below, the veneer to be analyzed in the NIR analysis station 420 is positioned in NIR analysis station 420. In the specific illustrative example of FIG. 10, veneer ribbon 1030 is rotary cut from preconditioned wood source 1001, such as a preconditioned peeler log.

[0360] In one embodiment, the veneer ribbon 1030 to be analyzed is positioned such that a veneer ribbon first surface 1032 of the veneer ribbon 1030 to be analyzed is illuminated by the illumination source 422 and a sample portion of veneer ribbon first surface 1032 is within view and focus of NIR camera 424. In one embodiment, the veneer ribbon 1030 is positioned in the NIR analysis station 420 by passing the veneer ribbon 1030 through the NIR analysis station 420 on a conveyor system.

[0361] In various embodiments, the one or more NIR cameras, such as NIR camera 424, can be of any resolution desired. As noted above, when the one or more NIR cameras, such as NIR camera 424, are used to scan the veneer ribbon first surface 1032 of a veneer ribbon 1030 for irregularities and create an NIR image data 462 of the veneer ribbon first surface 1032, essentially each pixel generated by NIR camera 424 is a sample point. Consequently, the resolution and accuracy of the surface irregularity detection process is only limited by the number of pixels the NIR camera 424 has covering the field of view, e.g., the entire veneer ribbon first surface 1032 of veneer ribbon 1030. Consequently, in the case where NIR camera 424 is a 1.3 mega pixel camera, there are essentially 1,400,000 individual measurement points on the veneer ribbon first surface 1032. In addition, NIR wavelengths are in the range of 750 nanometers (nm) to 4500 nm which are much smaller that the visible wavelengths of 480 to 740 nm. Consequently, using NIR cameras, such as NIR camera 424, results in resolutions and accuracy that simply cannot be achieved using traditional surface magnified visual image methods.

[0362] Therefore, using NIR cameras, such as NIR camera 424, system 1000 is capable of detecting irregularities in a wide range of samples sizes ranging from of a traditional 2″×2″ square, to a full 4′×10′ sheet or panel surface, and, by using a series of NIR images spliced together, up to a 100′-120′ ribbon of material. This, in turn, allows the disclosed embodiments to be implemented without significantly slowing down the production process or increasing the cost of the finished veneer.

[0363] As seen in FIG. 10, in this specific illustrative example, production floor environment 401 also includes adjustment implementation module 1096 for making relative real time adjustment to processing parameters for preconditioned wood source 1001 to generate veneer ribbon 1030 and processing control module 1098 which controls the processing of preconditioned wood source 1001 to generate veneer ribbon 1030.

[0364] As seen in FIG. 10, computing environment 450 includes computing system 452. As seen in FIG. 10, in one embodiment, computing system 452 includes surface irregularity to greyscale mapping database 410 containing mapping data 412 that maps surface irregularities to Near InfraRed (NIR) image greyscale values for one or more full veneer sheet, veneer strip, and/or partial veneer sheets.

[0365] As noted above with respect to FIG. 4A, using NIR images, extremely granular differences in irregularity levels can be detected. In general, locations with different levels of irregularities absorb/reflect different amounts of NIR radiation at specific frequencies. In operation, when NIR radiation of a given frequency is applied to a veneer ribbon first surface 1032 of veneer ribbon 1030, more NIR energy is reflected from surfaces that are perpendicular the NIR camera lens. Consequently, at locations having irregularities such that the surfaces are not perpendicular the NIR camera lens will appear darker, i.e., have a greater greyscale value.

[0366] When the NIR camera 424 takes an image of the veneer ribbon first surface 1032, the NIR camera 424 picks up the NIR energy reflected off veneer ribbon first surface 1032 at approximately 90 degrees. Consequently, when the NIR camera 424 takes an image of the veneer ribbon first surface 1032, the areas of irregularities, which scatter more NIR energy at angles other than 90 degrees and therefore reflect less NIR energy, appear darker than dry areas. In addition, the higher or more significant the irregularities that are present, the darker the area appears because less NIR energy is reflected to be captured by the NIR camera 424.

[0367] Using this fact, NIR image data 462 captured by the NIR camera 424 can be processed into NIR greyscale image data 464. Greyscale images can be of varying resolution, or bit, types. A 16-bit integer grayscale image provides 65535 available tonal steps from 0 (black) to 65535 (white). A 32-bit integer grayscale image theoretically will provide 4,2114,1167,2115 tonal steps from 0 (black) to 4211411672115 (white). Converting an NIR image based on these number of greyscale tonal steps results in a margin of error of significantly less than 0.1%.

[0368] In some embodiments, two or more NIR cameras are utilized, such as NIR camera 424, that are operated at different NIR frequencies and/or that are positioned a different angles with respect to veneer ribbon first surface 1032. This allows different types and levels of irregularities to be detected. In addition, using two or more NIR cameras, such as NIR camera 424, that are positioned at different angles means that different irregularities will have surfaces perpendicular to the camera lens and therefore will yield a 3-D effect when a composite NIR image is constructed. A more detailed discussion of a one example of a multi-NIR camera system is discussed above with respect to FIG. 4B.

[0369] Returning to FIG. 10, using the concepts discussed above, the mapping data 412 of surface irregularity to greyscale mapping database 410 is obtained through one or more empirical and/or manual processes, as discussed above with respect to FIG. 4A.

[0370] As discussed above, FIGS. 4C through 4H are illustrative examples of NIR images of surfaces of veneer produced various optimal and non-optimal production parameters. In the specific examples of FIGS. 4C through 4H the NIR image illustrations of 4C, 4D, 4E, 4F, 4G, and 4H, correlate to the magnified visual image illustrations of FIGS. 2A, 2B, 2C, 2D, 2E and 2F, respectively.

[0371] Returning the FIG. 10, computing system 452 also includes NIR greyscale image to processing parameter mapping database 1010. In one embodiment, NIR greyscale image to processing parameter mapping database 1010 includes processing parameter mapping data 1012 that maps NIR greyscale images to particular processing parameters and issues based on known data obtained from known processing greyscale images, such as images 4D, 4E, and 4H.

[0372] Computing system 452 also includes physical memory 460. In one embodiment, the physical memory 460 includes NIR image data 462 representing one or more NIR images of the illuminated veneer ribbon first surface 1032 of the veneer ribbon 1030 captured using NIR camera 424. Physical memory 460 also includes NIR greyscale image data 464. In one embodiment, computing system 452 includes one or more processors 470 for processing the NIR image data representing one or more NIR images of the illuminated veneer ribbon first surface 1032 of the veneer ribbon 1030 to generate NIR greyscale image data 464 indicating different irregularity levels and types in the illuminated veneer ribbon first surface 1032 of the veneer ribbon 1030.

[0373] In one embodiment, processor 470 processes the NIR greyscale image data 464 using the mapping data 412 from surface irregularity to greyscale mapping database 410 to identify irregularity levels and types for the veneer ribbon first surface 1032 of the veneer ribbon 1030.

[0374] As seen in FIG. 10, in one embodiment, computing system 452 includes a processing parameter analysis module 1074 which analyzes processing parameter mapping data 1012 and NIR greyscale image data 464 to determine a processing parameter maladjustment or issue represented by processing parameter mapping data 1012. In various embodiments, processing parameter analysis module 1074 determines which, if any, processing parameters must be changed to adjust the processing of subsequent veneer ribbon 1030 from the same wood source 1001.

[0375] In some embodiments, processing parameter analysis module 1074 includes one or more machine learning based models such as any machine learning based models discussed herein, and/or as known in the art at the time of filing, and/or as become known/available after the time of filing.

[0376] For instance, based on the analysis of NIR greyscale image data 464 and processing parameter mapping data 1012, processing parameter analysis module 1074 may determine: a knife or other processing component needs replacement; a probability that a rotation speed of a lath turning the wood source 1001 needs adjusting; an angle of a knife used to cut the veneer ribbon 1030 from the wood source 1001 needs adjusting; and a pressure used to keep a knife used to cut veneer ribbon 1030 from the wood source 1001 in contact with a surface of the wood source 1001 needs adjustment or a repair.

[0377] Processing parameter analysis module 1074 may determine any combination, or all, of these processing parameters, or other processing parameters, need to be adjusted. In various embodiments, the adjustments determined to be necessary by processing parameter analysis module 1074 are then provided to processing parameter adjustment activation module 1090 which is used to generate determined adjustment data 1094.

[0378] In various embodiments, determined adjustment data 1094 is then transferred to adjustment implementation module 1096 in production floor environment 401. Adjustment implementation module 1096 then causes processing control module 1098 to make the desired adjustments to the processing of preconditioned wood source 1001 into veneer ribbon 1030. As noted, these adjustments can include replacing a knife or other processing component; adjusting a rotation speed of a lath turning the wood source 1001; adjusting an angle of a knife used to cut the veneer ribbon 1030 from the wood source 1001; and adjusting or making repairs so that a pressure used to keep a knife used to cut veneer ribbon 1030 from the wood source 1001 in contact with a surface of the wood source 1001.

[0379] Using system 1000 the processing parameters so critical to veneer ribbon 1030 production can be adjusted dynamically using feedback based on actual veneer NIR surface image analysis. In one embodiment, these adjustments are made as veneer ribbon 1030 is being created from a single wood source 1001, such as a single preconditioned log. Consequently, using system 1000, provides a technical solution to the long-standing technical problem of adjusting processing parameters for optimal results from a single wood source before significant amounts of defective veneer have been produced to minimize wasted product and maximize product value in relative real time.

[0380] Those of skill in the art will ready recognize that the specific illustrative examples of one embodiment of a production floor environment 401 and components shown in FIG. 10 are but specific examples of numerous possible production environments and arrangement of physical components. Consequently, the specific illustrative example of an embodiment of a production floor environment 401 and components shown in FIGS. 10 is not intended to limit the scope of the invention as set forth in the claims below.

[0381] As a specific illustrative example of potential variations, in various embodiments, the NIR analysis station 420 can include one or more illumination sources 422 positioned to illuminate two or more surfaces of veneer ribbon 1030 and one or more NIR cameras 424 positioned to capture one or more NIR images of the two or more illuminated surfaces of veneer ribbon 1030.

[0382] As a further specific illustrative example of variations possible, additional input data can be considered such as current ambient temperature and humidity. The combination of these parameters can be analyzed by an AI/ML algorithm to further refine the production parameters for overall process efficiency.

[0383] These and numerous other variations are possible and contemplated by the inventors to be within the scope of the invention as set forth in the claims below.

[0384] FIG. 11 is a flow chart of a process 1100 for adjusting processing parameters used to produce a veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets from a wood source based on a level of irregularity of a first surface of the veneer ribbon, full veneer sheet, veneer strip, and/or partial veneer sheets in accordance with one embodiment.

[0385] As seen in FIG. 11, process 1100 begins at BEGIN operation 1102 and then process proceeds to operation 1104. In one embodiment, at operation 1104 a surface irregularity level to greyscale mapping database is generated such as any database discussed above with respect to FIG. 4A, FIG. 10, FIGS. 2A through 2C, and corresponding FIGS. 4D through 4H. In one embodiment, the surface irregularity level to greyscale mapping database contains mapping data that maps surface irregularities to Near InfraRed (NIR) image greyscale values for veneer.

[0386] Once a surface irregularity level to greyscale mapping database is generated at operation 1104, process flow proceeds to operation 1105. In one embodiment, at operation 1105 an NIR greyscale image to processing parameter mapping database is generated using any of the methods and systems discussed above with respect to FIG. 10.

[0387] Once an NIR greyscale image to processing parameter mapping database is generated at operation 1105, process flow proceeds to operation 1106. At operation 1106, an NIR analysis station is provided. In one embodiment, the NIR analysis station is substantially similar to any NIR analysis station discussed above with respect to FIGS. 4A, 4B, and 10. As discussed above, in one embodiment, the NIR analysis station includes one or more sources of illumination positioned to illuminate a surface of the veneer and one or more NIR cameras positioned to capture one or more NIR images of the illuminated surface of the veneer.

[0388] Once an NIR analysis station is provided at operation 1106, process flow proceeds to operation 1108. In one embodiment, at operation 1108, the veneer to be analyzed is positioned in the NIR analysis station of operation 1106 such that a first surface of the veneer to be analyzed is illuminated by the one or more illumination sources using any of the methods and systems discussed above with respect to FIG. 4A, FIG. 10, FIGS. 2A through 2C, and corresponding FIGS. 4D through 4H.

[0389] Once the veneer to be analyzed is positioned in the NIR analysis station at 1108, process flow proceeds to operation 1110. In one embodiment, at operation 1110 the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the veneer using any of the methods and systems discussed above with respect to FIG. 4A, FIG. 10, FIGS. 2A through 2C, and corresponding FIGS. 4D through 4H.

[0390] Once the one or more NIR cameras of NIR analysis station take one or more NIR images of the illuminated first surface of the veneer at operation 1110, process flow proceeds to operation 1112.

[0391] In one embodiment, at operation 1112, the one or more NIR images of the illuminated first surface of the veneer of operation 1110 are processed using any of the methods and systems discussed above with respect to FIGS. 4A, 4B, FIG. 10, FIGS. 2D through 2F, and corresponding FIGS. 4D through 4H, to generate NIR greyscale images indicating different irregularities in the illuminated first surface of the veneer.

[0392] Once the one or more NIR images of the illuminated first surface of the veneer are processed to generate NIR greyscale images indicating different irregularities in the illuminated first surface of the veneer at operation 1112, process flow proceeds to operation 1113.

[0393] In one embodiment, at operation 1113, the NIR greyscale images are processed using the NIR greyscale image to processing parameter mapping database to determine processing parameter adjustments required using any of the methods and systems discussed above with respect to FIGS. 4A and 4B, FIG. 10, FIGS. 2D through 2F, and corresponding FIGS. 4D through 4H.

[0394] Once the NIR greyscale images are processed using NIR greyscale image to processing parameter mapping database to determine processing parameter adjustments at operation 1113, process flow proceeds to operation 1114.

[0395] In one embodiment, at operation 1114 any processing parameters that it is determined must be adjusted are adjusted via one or more actions such as any actions discussed above with respect to FIG. 10.

[0396] Once any processing parameters that it is determined must be adjusted are adjusted at operation 1114, process flow proceeds to END operation 1134 where process 1100 is exited to await new samples and/or data.

[0397] The disclosed embodiments utilize NIR cameras to scan the surface of veneer for irregularities and create an NIR image of the surface of the veneer. Since essentially each pixel of camera image data is a sample point, the resolution and accuracy of the surface irregularity detection process is only limited by the number of pixels the camera has covering the field of view, e.g., the entire first surface of veneer. Consequently, in the case where a 1.3 mega pixel camera is used there are essentially 1,400,000 individual measurement points on the surface of the veneer. In addition, NIR wavelengths are in the range of 750 nanometers (nm) to 4500 nm which are much smaller that the visible wavelengths of 480 to 740 nm. Consequently, the use of NIR cameras as disclosed herein results in resolutions and accuracy that simply cannot be achieved using traditional visual irregularity detection systems.

[0398] In addition, when, as disclosed herein, NIR cameras are used as the surface irregularity detection mechanism, if greater or less resolution is deemed necessary, a higher or lower mega-pixel camera can be selected to achieve the desired resolution for the process. This can be accomplished in a relatively simple and quick camera switch out procedure. In addition, NIR camera placement with respect to the sample under analysis can be adjusted such that a quality image can be obtained as long as there is a clear field of view between the veneer surface and NIR camera. Horizontal, vertical, or angled placements have no impact on the functionality of the NIR camera.

[0399] Therefore, the disclosed technical solution is capable of detecting irregularities in a wide range of samples sizes ranging from of a traditional 2″×2″ square, to a full 4′×8′ sheet or panel surface, and, by using a series of NIR images spliced together, up to an 80′-120′ ribbon of material. This, in turn, allows the disclosed embodiments to be implemented without significantly slowing down the production process or increasing the cost of the finished veneer.

[0400] The use of NIR cameras, as disclosed herein, eliminates the need for any offline magnification of the veneer or the need for the surface irregularity detection device, i.e., the NIR camera, to be close to the surface of the veneer. This allows for more flexible placement of the sample taking device, i.e., the NIR camera.

[0401] In addition, unlike visual based detection methods NIR cameras are virtually immune to ambient visible light and interference. Consequently, use of NIR cameras as disclosed herein is far more suitable for a physical production line environment.

[0402] Further, NIR technology has been determined to be safe, i.e., representing no hazards to workers or other devices, by several testing and safety agencies. Consequently, the use of the disclosed NIR based surface irregularity detection systems results in a safe, comfortable, and efficient workplace and production floor.

[0403] Using the disclosed embodiments, surface irregularities on the surface of full veneer sheet, veneer strip, and/or partial veneer sheets can be identified efficiently, effectively, and quickly, while the production line continues operation at normal speeds, consequently, implementation of the disclosed embodiments, does not slow down production speed or change product processing time.

[0404] As noted above, embodiments of the present disclosure provide an effective and efficient technical solution to the technical problem of accurately and efficiently grading veneer. In one embodiment, the disclosed NIR analysis systems are part of one or more veneer analysis systems In one embodiment, individual full veneer sheets and/or veneer strips and/or partial veneer sheets are provided to one or more veneer analysis systems.

[0405] In one embodiment, once the veneer is graded using the detected using the disclosed NIR analysis system such as any of the NIR analysis systems of FIGS. 3A. 3B, 5, 6, 7, 8, 9, 10, or 11, the veneer is then provided to a veneer stacking system that produces more consistently graded veneer stacks based, at least in part, on the grade assigned to the veneer by the disclosed the NIR analysis systems.

[0406] In one embodiment, the veneer stacking system is any veneer stacking system discussed herein, and/or as known in the art at the time of filing, and/or as developed/made available/becomes known after the time of filing capable of stacking veneer.

[0407] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/230,470 (attorney docket number BCC-013), filed Apr. 14, 2021, entitled “METHOD AND SYSTEM FOR FULL VENEER SHEET GRADING AND STACKING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0408] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/230,497 (attorney docket number BCC-017), filed Apr. 14, 2021, entitled “METHOD AND SYSTEM FOR VENEER STRIP GRADING AND STACKING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0409] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/256,804 (attorney docket number BCC-004CIP1), filed Jun. 24, 2021, entitled “METHOD AND SYSTEM FOR GRADING AND STACKING VENEER SHEETS USING NEAR INFRARED IMAGING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0410] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/356,805 (attorney docket number BCC-004CIP2), filed Jun. 24, 2021, entitled “METHOD AND SYSTEM FOR GRADING AND STACKING VENEER STRIPS USING NEAR INFRARED IMAGING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0411] In one embodiment, the veneer stacks of now consistently graded veneer are then provided to the disclosed local robotic panel assembly and pressing systems. In one embodiment, the disclosed local robotic panel assembly and pressing system includes one or more local robotic panel assembly cells.

[0412] In one embodiment, the disclosed local robotic panel assembly cells include: one or more veneer handling robots; one or more glue application robots; and, in some embodiments, one or more core handling robots. In accordance with the disclosed embodiments, the local robotic panel assembly cells are used to locally and independently utilize the stacks of now consistently graded veneer to produce stacks of layered wood product panels at, or near, the pressing stations. As disclosed, the local robotic panel assembly cells operate independently to assemble the stacks at static locations local to the pressing stations and as the stacks are required. Consequently, using the disclosed embodiments, the stacks of layered wood product panels are built independently and locally at the pressing stations thereby eliminating the need for traditional panel conveyors, traditional layered wood product panel assembly layup lines, and stack press delivery lines. This, in turn, eliminates thousands of moving parts and dozens of people from the layered wood product production process.

[0413] Consequently, using the disclosed embodiments, many of the shortcomings of prior art are minimized or by-passed/resolved. For instance, using the methods and systems for producing layered wood products disclosed herein there is the no need for traditional panel conveyors, traditional layered wood product panel assembly layup lines, nor stack press delivery lines. Therefore, the large physical size, e.g., hundreds of feet, of factory floor space required by prior art methods and systems are not needed.

[0414] In addition, as discussed below, using the disclosed embodiments, not only are there significant cost savings in the layered wood product production process, but the resulting layered wood products produced using the disclosed embodiments are of a higher and more consistent quality.

[0415] FIG. 12A is a high-level diagram of a local robotic panel assembly and pressing station 1200A in accordance with one embodiment. As seen in FIG. 12A, local robotic panel assembly and pressing station 1200A includes robotic panel assembly cell 1201A that is used to create green panel stacks, such as green panel stack 360A.

[0416] It is worth noting that green panel stack 360A of FIG. 12A produced by robotic panel assembly cell 1201A is virtually identical to green panel stack 360A of FIG. 3D, or any of the green panel stacks 360 of FIGS. 3C or FIG. 3D. Consequently, robotic panel assembly cell 1201A literally replaces all of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, including traditional layered wood product panel assembly layup line 350 and stack press delivery line 362. This alone means that local robotic panel assembly and pressing station 1200A eliminates the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators.

[0417] As also seen in FIG. 12A, once robotic panel assembly cell 1201A creates green panel stack 360A, green panel stack 360A is transferred to pre-press 370A and green panel stack 360A is loaded into pre-press 370A where the green panel stack 360A is subjected to cold pre-pressing in the same pre-pressing process as discussed above. In the press 370A green panel stack 360A is pressed to flatten out the structure and force out any air pockets that may exist in the green panel stack 360A and to create pre-pressed stack 361A.

[0418] Once pre-pressed stack 361A is created, pre-pressed stack 361A is conveyed to an unstacking mechanism (not shown) which feeds the layered wood structure panels making up pre-pressed stack 361A one at a time into slots of hot press 380A and is then subjected to hot pressing in the same pre-pressing process as discussed above. At hot press380A the layered wood structure panels making up pre-pressed stack 361A are subjected to further pressure and heat to further flatten and cure the layered wood structure panels making up pre-pressed stack 361A. The layered wood structure panels are then re-stacked to form cured layered wood panel product stack 363A.

[0419] Cured layered wood panel product stack 363A is then conveyed to panel trim, quality analysis, and shipping area 311 where the individual layered wood panels making up cured layered wood panel product stack 363A are trimmed to size, subjected to quality control analysis, and then shipped to customers.

[0420] As noted, the pressing and trimming/quality control/shipping process shown in FIG. 12A is virtually identical to the pressing and finishing/quality control/shipping process discussed above with respect to FIG. 3D. Thus, according to one embodiment, once robotic panel assembly cell 1201A creates green panel stack 360A, green panel stack 360A is processed in the same manner, and using the same equipment, as is used to traditionally process layered wood products. Consequently, existing cold and hot press equipment need not be replaced. Therefore, the use of the disclosed local robotic panel assembly and pressing station 1200A results in eliminating the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, while still minimizing the amount of processing equipment that must be replaced.

[0421] According to the disclosed embodiments, multiple local robotic panel assembly and pressing stations, such as local robotic panel assembly and pressing station 1200A, can be operated at once, and independently, to form a robotic panel assembly and pressing system 1220.

[0422] FIG. 12B is a diagram of a robotic panel assembly and pressing system 1220 including four local robotic panel assembly and pressing stations 1200A through 1200D in accordance with one embodiment. In practice, the number of local robotic panel assembly and pressing stations can be fewer, or more, than the four shown in FIG. 12B.

[0423] As seen in FIG. 12B, each of local robotic panel assembly and pressing stations 1200A, 1200B, 1200C, and 1200D includes its own independently operating robotic panel assembly cell 1201A, 1201B, 1201C, and 1201D, respectfully, that are used to independently create green panel stacks 360A, 360B, 360C, and 360D.

[0424] It is worth noting again that green panel stacks 360A, 360B, 360C, and 360D of FIG. 12B produced by local robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D are virtually identical to green panel stacks 360A, 360B, 360C, and 360D of FIGS. 3C and 3D. Consequently, the set of local robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D literally replaces all of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, including traditional layered wood product panel assembly layup line 350 and stack press delivery line 362. This alone means that the set of local robotic panel assembly and pressing stations 1200A, 1200B, 1200C, and 1200D eliminates the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators.

[0425] As also seen in FIG. 12B, once local robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D create green panel stacks 360A, 360B, 360C, and 360D, green panel stacks 360A, 360B, 360C, and 360D are transferred to pre-presses 370A, 370B, 370C, and 370D, respectively, where the green panel stacks 360A, 360B, 360C, and 360D are subjected to cold pre-pressing. In the pre-presses 370A, 370B, 370C, and 370D, green panel stacks 360A, 360B, 360C, and 360D are pressed to flatten out the structures and force out any air pockets that may exist in the green panel stacks 360A, 360B, 360C, and 360D and to create pre-pressed stacks 361A, 361B, 361C, and 361D by the same pre-pressing process as discussed above.

[0426] Once pre-pressed stacks 361A, 361B, 361C, and 361D are created, pre-pressed stacks 361A, 361B, 361C, and 361D are conveyed into one or more unstacking mechanisms (not shown) which feed one layered wood structure panel at a time from the pre-pressed stacks 361A, 361B, 361C, and 361D into slots of one or more multi opening hot presses 380A, 380B. 380C, and 380D, respectively. At hot presses 380A, 380B, 380C, and 380D the layered wood structure panels making up pre-pressed stacks 361A, 361B, 361C, and 361D are subjected to further pressure and heat to further flatten and cure the layered wood structure panels making up pre-pressed stacks 361A, 361B, 361C, and 361D by the same hot pressing process as discussed above. Then the layered wood structure panels are re-stacked resulting in cured layered wood panel product stacks 363A, 363B, 363C, and 363D, respectively.

[0427] Cured layered wood panel product stacks 363A, 3634B, 363C, and 363D are then conveyed by conveyor 1260 to panel trim, quality analysis, and shipping area 311 where the individual layered wood panels making up cured layered wood panel product stacks 363A, 3634B, 363C, and 363D are trimmed to size, subjected to quality control analysis, and then shipped to customers.

[0428] The pressing and trimming/quality control/shipping process shown in FIG. 12B is virtually identical to the pressing and finishing/quality control/shipping process discussed above with respect to FIG. 3D. Thus, according to one embodiment, once robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D create green panel stacks 360A, 360B, 360C, and 360D, green panel stacks 360A, 360B, 360C, and 360D are processed by local robotic panel assembly and pressing stations 1200A through 1200D in the same manner, and using the same equipment, as used to traditionally process layered wood products. Consequently, existing cold and hot press equipment need not be replaced. Therefore, the use of the disclosed robotic panel assembly and pressing system 1220 results in eliminating the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators of the prior art structure shown in FIG. 3C and the stack production and processing section 399 of FIG. 3D, while still minimizing the amount of processing equipment that must be replaced.

[0429] In addition, robotic panel assembly and pressing system 1220 has several other processing advantages over prior art systems. First, recall that using prior systems such as that shown in FIG. 3D, in addition to the cost of operating traditional layered wood product panel assembly layup and press line 351, including stack production and processing section 399, i.e., traditional layered wood product panel assembly layup line 350 and stack press delivery line 362, there was a significant cost associated with any delays in traditional layered wood product panel assembly layup and press line 351. These delays included delays due to failure of any of the thousands of moving parts associated with traditional layered wood product panel assembly layup and press line 351, and particularly stack production and processing section 399, or any human error introduced by the twelve or more people required to operate traditional layered wood product panel assembly layup and press line 351.

[0430] Further recall that, referring to FIGS. 3D and 3F together, when a delay occurred, for whatever reason, the layers of glue applied by glue applicators 309A through 309J could dry out before the green panel stacks 360 reached the pressing stations 353 through 359. This, in turn, resulted in layered wood product panels that could separate or otherwise fail because the glue could not cure and adhere the layers properly. Unfortunately, this resulted in significant loss of product using traditional layered wood product panel assembly layup and press line 351. Currently there is an average loss of product to defects of ten percent or more using traditional layered wood product panel assembly layup and press line 351.

[0431] However, referring back to FIG. 12B, in direct contrast to prior art systems, using independently operating robotic panel assembly and pressing system 1220, the green panel stacks 360A, 360B, 360C, and 360D are independently built at individual static locations at, or near, the pressing area by individual and independently operating robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D. Consequently, using robotic panel assembly and pressing system 1220 if there is a delay in any of the local robotic panel assembly and pressing stations 1200A through 1200D, the delay only affects the panels being processed by that particular local robotic panel assembly and pressing station, i.e., only one of pressing stations 1200A through 1200D. As a result, any such delay can, at most, cause a single stack of panels to be lost. This is in direct contrast to the multiple stacks that can be lost as a result of delays in traditional layered wood product panel assembly layup and press line 351. The product savings can literally be an order of magnitude or more as a delay in traditional layered wood product panel assembly layup and press line 351 can result in the loss of four hundred or more individual layered wood product panels while a delay in any of local robotic panel assembly and pressing stations 1200A through 1200D would typically result in, at most, forty individual layered wood product panels.

[0432] In addition, as noted above, using prior art methods and systems for producing layered wood products, such as using traditional layered wood product panel assembly layup and press line 351, material and glue systems are configured to run a single product at a time, i.e., only a single ply count panel, or single type of product (plywood or PLV), at a time. Changing products required stopping the machine, removing all in process material, and then reconfiguring controls for new product construction.

[0433] However, and again in direct contrast to prior art systems, using robotic panel assembly and pressing system 1220, and local robotic panel assembly and pressing stations 1200A through 1200D, the green panel stacks 360A, 360B, 360C, and 360D are built independently at individual static locations at, or near, the pressing area by individual robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D. As a result, each of the local robotic panel assembly and pressing stations 1200A through 1200D can independently generate different products. Consequently, each of the local robotic panel assembly and pressing stations 1200A through 1200D can produce different ply count panels, or different types of products, plywood or PLV, independently and at the same time.

[0434] The fact that using robotic panel assembly, and pressing system 1220, local robotic panel assembly and pressing stations 1200A through 1200D, green panel stacks 360A, 360B, 360C, and 360D are built at independently operating individual static locations at or near the pressing area by individual robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D eliminates the issues discussed above associated with prior art systems where it was critical to ensure coordination between the stacker operator SO and each of the press operators PO1, PO2, PO3, and PO4 of FIGS. 3C and 3D so that the wrong size stacks were not loaded into a pre-press or hot press that is unable to process them.

[0435] FIG. 12C is a more detailed diagram of a robotic panel assembly cell 1201A of FIGS. 12A and 12B in accordance with one embodiment.

[0436] Robotic panel assembly cell 1201A is exemplary of any of the individual robotic panel assembly cells 1201A, 1201B, 1201C, and 1201D of FIGS. 12A and 12B. As seen in FIG. 12C, robotic panel assembly cell 1201A is used to create green panel stack 360A which is itself exemplary of any of the green panel stacks 360A, 360B, 360C, and 360D of FIG. 12A and 2B.

[0437] As seen in FIG. 12C, robotic panel assembly cell 1201A includes veneer stack 1298A and core stack 1299A. In one embodiment, veneer stack 1298A is a stack of full sheets of veneer created using once or more of the disclosed NIR analysis systems and stacking systems discussed above with respect to FIGS. 4A, 4B, 4C through 4G, 5, 6, 7, 8, 9, 10, and 11.

[0438] In one embodiment, core stack 1299A is a stack of core material that can include portions of veneer sheets, and/or veneer strips, and/or partial veneer sheets created using once or more of the disclosed NIR analysis systems and any of the stacking systems discussed above with respect to FIGS. 4A, 4B, 4C through 4G, 5, 6, 7, 8, 9, 10, and 11.

[0439] As discussed in more detail above with respect to FIG. 4A and referring to FIGS. 4A and 12C, in some embodiments, selected action data 494 is forwarded to an action activation module, such as selected action implementation module 496, in production floor environment 401 to initialize one or more actions with respect to the veneer 430 based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 by action selection and activation module 490. These actions can include assigning the veneer 430 to a specific veneer stack, such as veneer stack 1298A or core stack 1299A, associated with the grade assigned to the veneer 430.

[0440] As also discussed in more detail above, in some embodiments, the selected action indicated by selected action data 494 is to add veneer 430 to a specific veneer stack, such as veneer stack 1298A or core stack 1299A, based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430. In these embodiments, grade assignment data 482 is provided to action selection and activation module 490 which, in turn, forwards grade assignment data 482 to selected action implementation module 496. In one embodiment, selected action implementation module 496 then forwards grade assignment data 482 to a stacking system such as any stacking system discussed herein. As discussed in more detail below, in these embodiments, the veneer 430 is then added to a specific veneer stack, such as veneer stack 1298A or core stack 1299A, based, at least in part, on the grade represented by grade assignment data 482 and assigned to the veneer 430 and the grading data for the stack, such as veneer stack 1298A or core stack 1299A, is also provided to control system 1202.

[0441] In one embodiment, the veneer stacking system is any veneer stacking system discussed herein, and/or as known in the art at the time of filing, and/or as developed/made available /becomes known after the time of filing capable of stacking veneer.

[0442] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/230,470 (attorney docket number BCC-013), filed Apr. 14, 2021, entitled “METHOD AND SYSTEM FOR FULL VENEER SHEET GRADING AND STACKING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0443] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/230,497 (attorney docket number BCC-017), filed Apr. 14, 2021, entitled “METHOD AND SYSTEM FOR VENEER STRIP GRADING AND STACKING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0444] Returning to FIG. 12C, robotic panel assembly cell 1201A includes veneer handling robot 1251 which is representative of one or more veneer handling robots; glue application robot 1255 which is representative of one or more glue application robots; and, in some embodiments where plywood green layered wood product panel stacks are to be produced, core handling robot 1253 which is representative of one or more core handling robots.

[0445] Also seen in FIG. 12C is control system 1202 which is used to control veneer handling robot 1251, core handling robot 1253, and glue application robot 1255. In various embodiments, control system 1202 is representative of one or more computing systems which generate instructions for veneer handling robot 1251, core handling robot 1253, and glue application robot 1255 in the form of control signals. In this way, control system 1202 directs veneer handling robot 1251, core handling robot 1253, and glue application robot 1255 in the construction of the green panel stack 360A via the generated control signals and according to the grade of the veneer making up veneer stack 1298A and/or core stack 1299A.

[0446] In one embodiment, veneer handling robot 1251 is directed by the control signals from control system 1202 to retrieve veneer sheets from veneer stack 1298A and place the veneer sheet on green plywood panel stack 360A in accordance with received control signals to create the green layered wood product panels 1241 and 1243 in green panel stack 360A as discussed above and as shown in FIG. 12C.

[0447] In one embodiment, glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue from glue reservoir 1256 between sheets of veneer and/or core material in accordance with received control signals to create the green layered wood product panels 1241 and 1243 in green panel stack 360A as discussed above and as shown in FIG. 12C.

[0448] In embodiments where robotic panel assembly cell 1201A is used to create green plywood panels 1241 and a green plywood panel stack 360A, robotic panel assembly cell 1201A includes core handling robot 1253. In one embodiment, core handling robot 1253 is directed by the control signals from control system 1202 to retrieve core material from core stack 1299A and place a portion of core material on green plywood panel stack 360A in accordance with received control signals to create the green plywood panels 1241 and 1243 in green plywood panel stack 360A as discussed above and as shown in FIG. 12C.

[0449] Robots, such as veneer handling robot 1251, glue application robot 1255, and core handling robot 1253 are generally known in the art, at least generically as systems for handling materials and performing various tasks in response to control signals from one or more control systems. Consequently, a detailed description of the general structure and operation of robots is omitted here to avoid detracting from the invention. However, the tasks performed by veneer handling robot 1251, glue application robot 1255, and core handling robot 1253 and the use of veneer handling robot 1251, glue application robot 1255, and core handling robot 1253 to produce green layered wood panel stacks, such as green panel stack 360A are not known in the art and therefore the functions performed by veneer handling robot 1251, glue application robot 1255, and core handling robot 1253 are described in detail.

[0450] In particular, as shown in FIG. 12C, veneer handling robot 1251 is first directed by control signals from control system 1202 to retrieve veneer sheet 1271 from the stack of veneer sheets 1298A and place the veneer sheet 1271 on green panel stack 360A.

[0451] Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1281 from glue reservoir 1256 to veneer sheet 1271.

[0452] In embodiments where robotic panel assembly cell 1201A is used to create green plywood panels, then core handling robot 1253 is directed by the control signals from control system 1202 to retrieve core material from core stack 1299A and place a portion of core material on green panel stack 360A to create core layer 1291.

[0453] Glue application robot 1255 is then directed by the control signals from control system 1202 to apply a layer of glue 1283 from glue reservoir 1256 on core layer 1291. Then veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1273 from the stack of veneer sheets 1298A and place the veneer sheet 1273 on green layered wood product panel 360A.

[0454] Of note, in embodiments where robotic panel assembly cell 1201A is used to produce green layered wood product stacks of other types of layered wood products, such as green PLV panels, core handling robot 1253 is either deactivated or not present. In these cases, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1271 from the stack of veneer sheets 1298A and place the veneer sheet 1271 on green panel stack 360A. Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1281 from glue reservoir 1256 to veneer sheet 1271. Then veneer handling robot 1251 is simply directed by control signals from control system 1202 to retrieve another veneer sheet 1273 from the stack of veneer sheets 1298A and place the veneer sheet 1273 on veneer sheet 1271.

[0455] The result of the operations above is a three-ply green layered wood product panel 1241. As noted above, plywood, and other layered wood product panels often have twenty-one or more plys. However, for simplicity of illustration, green layered wood product panel 1241 is a three-ply green layered wood product panel 1241.

[0456] Once green layered wood product panel 1241 is constructed by robotic panel assembly cell 1201A, robotic panel assembly cell 1201A begins to construct a second green layered wood product panel 1243 of green panel stack 360A. To this end, veneer handling robot 1251 is again directed by control signals from control system 1202 to retrieve a veneer sheet 1275 from the stack of veneer sheets 1298A and place the veneer sheet 1275 on the glue-free side of veneer sheet 1273. Importantly, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1275 from the stack of veneer sheets 1298A and place the veneer sheet 1275 on the veneer sheet 1273 directly, without any glue layer being applied by glue application robot 1255. This creates a dry veneer to veneer layer, or gap 1240. Gap 1240 therefore separates green layered wood product panel 1241 and green layered wood product panel 1243 in green panel stack 360A.

[0457] Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1285 from glue reservoir 1256 to veneer sheet 1275. In embodiments where robotic panel assembly cell 1201A is used to create green plywood panels, then core handling robot 1253 is directed by the control signals from control system 1202 to retrieve core material from core stack 1299A and place a portion of core material on green panel stack 360A to create core layer 1293. Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1287 from glue reservoir 1256 on core layer 1293. Then veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1277 from the stack of veneer sheets 1298A and place the veneer sheet 1277 on green panel stack 360A.

[0458] Of note again, in embodiments where robotic panel assembly cell 1201A is used to produce green layered wood product stacks of other types of layered wood products, such as green PLV panels, core handling robot 1253 is either deactivated or not present. In these cases, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1275 from the stack of veneer sheets 1298A and place the veneer sheet 1275 on green panel stack 360A. Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1285 from glue reservoir 1256 to veneer sheet 1275. Then veneer handling robot 1251 is simply directed by control signals from control system 1202 to retrieve another veneer sheet 1277 from the stack of veneer sheets 1298A and place the veneer sheet 1277 on veneer sheet 1275.

[0459] The result of the operations above is a second three-ply green layered wood product panel 1243. The process above is then repeated to create the desired number of green layered wood product panels for green panel stack 360A. As noted above, it is not uncommon for green panel stack 360A to include forty or more individual green layered wood product panels.

[0460] It is worth noting again that green panel stack 360A of FIG. 12C produced by robotic panel assembly cell 1201A is virtually identical to green panel stack 360A of FIG. 3D, or any of the green panel stacks 360 of FIGS. 1D or FIG. 3D. Consequently, robotic panel assembly cell 1201A literally replaces all of the prior art structure shown in FIG. 3C and the stack production and processing section 399 of FIG. 3D, including traditional layered wood product panel assembly layup line 350 and stack press delivery line 362. This alone means that local robotic panel assembly and pressing station 1200A eliminates the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators.

[0461] In addition, according to the disclosed embodiments, and in contrast to prior art systems, robotic panel assembly cell 1201A is located locally at, or near, pre-press 370A and hot press 380A. Therefore, green panel stack 360A is assembled by robotic panel assembly cell 1201A locally with respect to the pressing line. Consequently, robotic panel assembly cell 1201A assembles the same green panel stack 360A as any of the green panel stacks 360 of FIGS. 3C or FIG. 3D locally with respect to pre-press 370A and hot press 380A and at a single location.

[0462] As seen in FIG. 12A, once robotic panel assembly cell 1201A creates green panel stack 360A, green panel stack 360A is transferred to pre-press 370A and green panel stack 360A is loaded into pre-press 370A where the green panel stack 360A is subjected to cold pre-pressing. In the pre-press 370A green panel stack 360A is pressed to flatten out the structure and force out any air pockets that may exist in the green panel stack 360A and to create pre-pressed stack 361A.

[0463] Once pre-pressed stack 361A is created, pre-pressed stack 361A is conveyed to an unstacking mechanism (not shown) which feeds the layered wood structure panels making up pre-pressed stack 361A one at a time into slots of hot press 380A. At hot press380A the layered wood structure panels making up pre-pressed stack 361A are subjected to further pressure and heat to further flatten and cure the layered wood structure panels making up pre-pressed stack 361A. The layered wood structure panels are then re-stacked to form cured layered wood panel product stack 363A.

[0464] Cured layered wood panel product stack 363A is then conveyed to panel trim, quality analysis, and shipping area 311 where the individual layered wood panels making up cured layered wood panel product stack 363A are trimmed to size, subjected to quality control analysis, and then shipped to customers.

[0465] In one embodiment, the pressing and trimming/quality control/shipping process shown in FIG. 12A is virtually identical to the pressing and finishing/quality control/shipping process discussed above with respect to FIG. 3D. Thus, according to one embodiment, once robotic panel assembly cell 1201A creates green panel stack 360A, green panel stack 360A is processed in the same manner, and using the same equipment, as is used to traditionally process layered wood products. Consequently, existing cold and hot press equipment need not be replaced. Therefore, the use of the disclosed local robotic panel assembly and pressing station 1200A results in eliminating the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, while still minimizing the amount of processing equipment that must be replaced.

[0466] As discussed above, the same layering of veneer that potentially provides so many advantages in layered wood products can also present some drawbacks. For instance, the presence of irregular surfaces in the layered sheets of veneer, i.e., inconsistent surface texture and moisture content, can create problems, such as cracks or other defects, in the layered wood products. This, of course, can result in compromised structural integrity of the layered wood products and/or undesirable imperfections in the layered wood products. Consequently, it is critical to accurately and efficiently determine the surface texture and moisture content of the veneer sheets used in a layered wood products. However, accurately, effectively, and efficiently determining the surface texture and moisture content of the veneer sheets used in layered wood products has historically been a difficult technical problem to solve.

[0467] Consequently, prior art methods and systems for producing layered wood products typically do not include any process for inspecting or grading veneer sheets used in the production of layered wood products. As a result, using prior art methods and systems for producing layered wood products, the quality of veneer fed into process was not inspected during feeding operation. Therefore, undetected defects often caused panels to be rejected only downstream after significant time and energy had already been devoted to the panels, i.e., pressing is complete and panel quality is analyzed.

[0468] Using the disclosed NIR analysis systems and stacking systems discussed above with respect to FIGS. 4A, 4B, 4C through 4G, 5, 6, 7, 8, 9, 10, and 11 the surface texture of veneer used in layered wood products can be determined before the veneer is processed. In addition, several recently discovered technical solutions to the technical problem of accurately and efficiently determining the surface texture and moisture content of the veneer sheets used in a layered wood products are set forth in the related U.S. Patent Applications incorporated by reference above. These disclosed quality inspection methods and systems can also be used to determine the surface texture and moisture of veneer sheets used in layered wood products before the veneer is processed.

[0469] In one embodiment, the disclosed method and system for producing layered wood products takes advantage of the disclosed NIR analysis systems and stacking systems discussed above with respect to FIGS. 4A, 4B, 4C through 4G, 5, 6, 7, 8, 9, 10, and 11 and/or these other innovations to inspect and grade the veneer used in the disclosed method and system for producing layered wood products. To this end, in one embodiment, the disclosed local robotic panel assembly and pressing stations include a veneer analysis system. In one embodiment, the veneer analysis system includes inspection/grading robot which is used to determine the quality of veneer fed into process during feeding operation. Therefore, defects can be detected, and the veneer sheets can be graded before significant time and energy has already been devoted to the panels. In one embodiment, the

[0470] FIG. 12D is a diagram of a local robotic panel assembly cell 1211A that is similar to robotic panel assembly cell 1201A of FIGS. 12A, 12B, and 12C but that includes a veneer analysis system 1204 and multiple graded veneer stacks 1206, 1208, 1210 and 1212 in accordance with one embodiment.

[0471] The operation of local robotic panel assembly cell 1211A is substantially similar to the operation of robotic panel assembly cell 1201A of FIGS. 12A, 12B, and 12C. However, before veneer sheets from veneer stack 1303A are made available to veneer handling robot 1251 the veneer sheets are retrieved by veneer inspection/grading robot 1245 which is representative of one or more veneer inspection/grading robots. Veneer inspection/grading robot 1245 then presents each veneer sheet to the veneer analysis system 1204 in accordance with control signals from control system 1202.

[0472] At the veneer analysis system 1204 the veneer sheets are inspected and assigned a grade based on the inspection results. In one embodiment, veneer analysis system 1204 includes one or more of the disclosed NIR analysis systems discussed above with respect to FIGS. 4A, 4B, 4C through 4G, 5, 6, 7, 8, 9, 10, and 11 to detect surface irregularities, moisture levels, density, and to assign a grade to the veneer sheets of veneer stack 1303A.

[0473] In one embodiment, veneer analysis system 1204 can also utilize one or more inspection methods and systems such as any of those set forth in the related U.S. Patent Applications incorporated by reference above. For example, Veneer analysis system 1204 can utilize one of more visible light inspection systems and/or one or more Near Infrared (NIR) inspection systems and/or superimposed imaging to detect surface irregularities, moisture levels, density, and to assign a grade to the veneer sheets of veneer stack 1303A.

[0474] In one embodiment, the veneer stacking system is any veneer stacking system discussed herein, and/or as known in the art at the time of filing, and/or as developed/made available /becomes known after the time of filing capable of stacking veneer.

[0475] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/230,470 (attorney docket number BCC-013), filed Apr. 14, 2021, entitled “METHOD AND SYSTEM FOR FULL VENEER SHEET GRADING AND STACKING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0476] In one embodiment, the veneer stacking system is an improved veneer stacking system such as any of those disclosed in Bolton et al., U.S. patent application Ser. No. 17/230,497 (attorney docket number BCC-017), filed Apr. 14, 2021, entitled “METHOD AND SYSTEM FOR VENEER STRIP GRADING AND STACKING,” which is hereby incorporated by reference in its entirety as if it were fully set forth herein.

[0477] In one embodiment, based on the grade assigned to each veneer sheet, each veneer sheet is placed in one of graded veneer stacks, such as graded veneer stacks 1206, 1208, 1210 and 1212 of FIG. 12D by veneer inspection/grading robot 1245. In one embodiment, veneer stack 1206 is a grade 1 veneer stack that includes veneer sheets that are deemed to be of acceptable appearance and quality to be used for outer veneer layers of a layered wood panel. In one embodiment, veneer stack 1208 is a grade 2 veneer stack that includes veneer sheets that are deemed to be of acceptable structural quality to be used for inner veneer layers of a layered wood panel but perhaps lack the appearance to be used as outer layers of a layered wood panel. In one embodiment, veneer stack 1210 is a grade 3 veneer stack that includes veneer sheets that are deemed to have structural anomalies, such as knot holes, and therefore must be sparingly used for inner veneer layers of a layered wood panel and perhaps must be sandwiched between higher grade veneer sheets to provide adequate structural quality for the layered wood panel. Finally, in one embodiment, trash 1212 contains veneer sheets of unacceptable quality.

[0478] By grading veneer sheets from veneer stack 1303A and stacking the veneer sheets according to grade, the quality of veneer fed into process during feeding operation is again determined before resources are expended processing the veneer, i.e., defects can be detected in the veneer sheets, and the veneer sheets can be graded, and allocated for their best use, before significant time and energy is devoted to their use in processed panels.

[0479] Once the veneer sheets from veneer stack 1303A are inspected/graded by inspection grading system 1204, and the sheets are placed in appropriate graded veneer stacks 1206, 1208, 1210 and 1212 by veneer inspection/grading robot 1245. In one embodiment, robotic panel assembly cell 1211A operates the same way as robotic panel assembly cell 1201A of FIGS. 12A, 12B, and 12C.

[0480] In particular, as shown in FIG. 12D, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1271 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1271 on green panel stack 360A.

[0481] Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1281 from glue reservoir 1256 to veneer sheet 1271.

[0482] In embodiments where robotic panel assembly cell 1211A is used to create green plywood panels, then core handling robot 1253 is directed by the control signals from control system 1202 to retrieve core material from core stack 1299A and place a portion of core material on green panel stack 360A to create core layer 1291.

[0483] Glue application robot 1255 is then directed by the control signals from control system 1202 to apply a layer of glue 1283 from glue reservoir 1256 on core layer 1291. Then veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1273 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1273 on green layered wood product panel 360A.

[0484] Of note, in embodiments where robotic panel assembly cell 1211A is used to produce green layered wood product stacks of other types of layered wood products, such as green PLV panels, core handling robot 1253 is either deactivated or not present. In these cases, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1271 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1271 on green panel stack 360A. Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1281 from glue reservoir 1256 to veneer sheet 1271. Then veneer handling robot 1251 is simply directed by control signals from control system 1202 to retrieve another veneer sheet 1273 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1273 on veneer sheet 1271.

[0485] The result of the operations above is a single three-ply green layered wood product panel 1241. As noted above, plywood, and other layered wood product panels often have twenty-one or more plys. However, for simplicity of illustration, green layered wood product panel 1241 is a single three-ply green layered wood product panel 1241.

[0486] Once green layered wood product panel 1241 is constructed by robotic panel assembly cell 1211A, robotic panel assembly cell 1211A begins to construct a second green layered wood product panel 1243 of green panel stack 360A. To this end, veneer handling robot 1251 is again directed by control signals from control system 1202 to retrieve veneer sheet 1275 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1275 on the glue-free side of veneer sheet 1273. Importantly, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1275 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1275 on the veneer sheet 1273 directly, without any glue layer being applied by glue application robot 1255. This creates a dry veneer to veneer layer, or gap 1240. Gap 1240 therefore separates green layered wood product panel 1241 and green layered wood product panel 1243 in green panel stack 360A.

[0487] Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1285 from glue reservoir 1256 to veneer sheet 1275. In embodiments where robotic panel assembly cell 1211A is used to create green plywood panels, then core handling robot 1253 is directed by the control signals from control system 1202 to retrieve core material from core stack 1299A and place a portion of core material on green panel stack 360A to create core layer 1293. Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1287 from glue reservoir 1256 on core layer 1293 Then veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1277 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1277 on green panel stack 360A.

[0488] Of note again, in embodiments where robotic panel assembly cell 1211A is used to produce green layered wood product stacks of other types of layered wood products, such as green PLV panels, core handling robot 1253 is either deactivated or not present. In these cases, veneer handling robot 1251 is directed by control signals from control system 1202 to retrieve veneer sheet 1275 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1275 on green panel stack 360A. Then glue application robot 1255 is directed by the control signals from control system 1202 to apply a layer of glue 1285 from glue reservoir 1256 to veneer sheet 1275. Then veneer handling robot 1251 is simply directed by control signals from control system 1202 to retrieve another veneer sheet 1277 from the appropriate graded veneer stack 1206, 1208, 1210 and place the veneer sheet 1277 on veneer sheet 1275.

[0489] The result of the operations above is a second single three-ply green layered wood product panel 1243. The process above is then repeated to create the desired number of green layered wood product panel for green panel stack 360A. As noted above, it is not uncommon for green panel stack 360A to include forty or more individual green layered wood product panels.

[0490] It is worth noting again that green panel stack 360A of FIG. 12D produced by robotic panel assembly cell 1211A is virtually identical to green panel stack 360A of FIG. 3D, or any of the green panel stacks 360 of FIGS. 1D or FIG. 3D. Consequently, robotic panel assembly cell 1211A literally replaces all of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, including traditional layered wood product panel assembly layup line 350 and stack press delivery line 362. This alone means that local robotic panel assembly and pressing station 1200A eliminates the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators.

[0491] In addition, according to the disclosed embodiments, and in contrast to prior art systems, robotic panel assembly cell 1211A is located locally at, or near, pre-press 370A and hot press 380A. Therefore, green panel stack 360A is assembled by robotic panel assembly cell 1211A locally with respect to the pressing line. Consequently, robotic panel assembly cell 1211A assembles the same green panel stack 360A as any of the green panel stacks 360 of FIGS. 3D or FIG. 3D locally with respect to pre-press 370A and hot press 380A and at a single location.

[0492] As seen in FIG. 12D, once robotic panel assembly cell 1211A creates green panel stack 360A, green panel stack 360A is transferred to pre-press 370A and green panel stack 360A is loaded into pre-press 370A where the green panel stack 360A is subjected to pre-pressing by the methods discussed above. In the cold press 370A green panel stack 360A is pressed to flatten out the structure and force out any air pockets that may exist in the green panel stack 360A and to create pre-pressed stack 361A.

[0493] Once pre-pressed stack 361A is created, pre-pressed stack 361A is conveyed to an unstacking mechanism (not shown) which feeds the layered wood structure panels making up pre-pressed stack 361A one at a time into slots of hot press 380A. At hot press 380A the layered wood structure panels making up pre-pressed stack 361A are subjected to further pressure and heat to further flatten and cure the layered wood structure panels making up pre-pressed stack 361A by the methods discussed above. The layered wood structure panels are then re-stacked to form cured layered wood panel product stack 363A.

[0494] Cured layered wood panel product stack 363A is then conveyed to panel trim, quality analysis, and shipping area 311 where the individual layered wood panels making up cured layered wood panel product stack 363A are trimmed to size, subjected to quality control analysis, and then shipped to customers.

[0495] The pressing and trimming/quality control/shipping process shown in FIG. 12D is virtually identical to the pressing and finishing/quality control/shipping process discussed above with respect to FIG. 3D. Thus, according to one embodiment, once robotic panel assembly cell 1211A creates green panel stack 360A, green panel stack 360A is processed in the same manner, and using the same equipment, as is used to traditionally process layered wood products. Consequently, existing cold and hot press equipment need not be replaced. Therefore, the use of the disclosed local robotic panel assembly and pressing station 1200A results in eliminating the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, while still minimizing the amount of processing equipment that must be replaced.

[0496] In some embodiments, a quality analysis and feedback cell for process refinement is included in a local robotic panel assembly cell. FIG. 13 is a diagram of a local robotic panel assembly and pressing station 1300 including a quality analysis and feedback cell 1301 for process refinement in accordance with one embodiment.

[0497] As seen in FIG. 13, once local robotic panel assembly cell 1201A creates green panel stack 360A, green panel stack 360A is transferred to pre-press 370A and green panel stack 360A is loaded into pre-press 370A where the green panel stack 360A is subjected to cold pre-pressing. In the pre-press 370A green panel stack 360A is pressed to flatten out the structure and force our any air pockets that may exist in the green panel stack 360A and to create pre-pressed stack 361A by the methods discussed above.

[0498] Once pre-pressed stack 361A is created, pre-pressed stack 361A is conveyed to an unstacking mechanism (not shown) which feeds the layered wood structure panels making up pre-pressed stack 361A one at a time into slots of hot press 380A. At hot press380A the layered wood structure panels making up pre-pressed stack 361A are subjected to further pressure and heat to further flatten and cure the layered wood structure panels making up pre-pressed stack 361A by the methods discussed above. The layered wood structure panels are then re-stacked to form cured layered wood panel product stack 363A.

[0499] Cured layered wood panel product stack 363A is then conveyed to panel trim, quality analysis, and shipping area 311 where the individual layered wood panels making up cured layered wood panel product stack 363A are trimmed to size, subjected to quality control analysis, and then shipped to customers.

[0500] FIG. 14A is a photograph of a structural density analysis report 1411 based on the results of processing using one type of wood product panel bond analyzer used in accordance with one embodiment.

[0501] As seen in FIG. 14A, in one embodiment, the wood panel exits the press and typically passes through the wood product panel bond analyzer (not shown) of quality analysis and feedback cell 1301. Typically, a wood product panel bond analyzer is configured to analyze and record the reading for each 3″×3″ square of the panel as it passes the ultrasonic heads. This size can be configured per customer requirements, with 3″ being common in wood products panel manufacturing. For each panel analyzed, the grader prepares a data file and represents it in a visual format. The top image 1413 is typically gray scale and the lower image 1411 being colorized. The customer can define the values required for quality and alert if those thresholds are not met. Numerous combinations of quality and number of adjacent squares can be considered per customer requirements.

[0502] FIG. 14B is a photograph of average panel thickness analysis report 1421 based on the results of processing using one type of wood product panel bond analyzer used in accordance with one embodiment.

[0503] FIG. 14C is a photograph of panel thickness trend analysis report 1423 based on the results of processing using one type of wood product panel bond analyzer used in accordance with one embodiment.

[0504] Referring to FIGS. 14B and 14C together, typically each panel is also measured for thickness. Alert points can be configured as to allow alerting when thresholds are exceeded. Panel thickness is often controlled by press pressure and/or press to position instrumentation allowing the press to compress the panel the required amount to produce a completed panel withing selected tolerances.

[0505] The pressing and trimming/quality control/shipping process shown in FIGS. 12A, 12B, 12C, 12D, and 13 is virtually identical to the pressing and finishing/quality control/shipping process discussed above with respect to FIG. 3D. Thus, according to one embodiment, once robotic panel assembly cell 1201A creates green panel stack 360A, green panel stack 360A is processed in the same manner, and using the same equipment, as is used to traditionally process layered wood products. Consequently, existing cold and hot press equipment need not be replaced. Therefore, the use of the disclosed local robotic panel assembly and pressing station 1200A results in eliminating the need for hundreds of square feet of floor space, thousands of moving parts, multiple sensors and motors, and dozens of sub-assemblies and human operators of the prior art structure shown in as FIG. 3C and the stack production and processing section 399 of FIG. 3D, while still minimizing the amount of processing equipment that must be replaced.

[0506] Referring to FIGS. 12C and 13 together, when the individual layered wood panels making up cured layered wood panel product stack 363A are subjected to quality control analysis at panel trim, quality analysis, and shipping area 311, quality parameter data, such as, but not limited to, the data discussed above with respect to FIGS. 4A, 4B, 4C, and 4D, regarding each layered wood panel making up cured layered wood panel product stack 363A is collected.

[0507] In various embodiments, this quality parameter data represents results from analysis of specific quality parameters and specific quality parameter values, such as density and thickness as discussed above.

[0508] In one embodiment, the specific quality parameters and specific quality parameter values of the quality parameter data obtained from the quality control analysis at panel trim, quality analysis and shipping area 311 is correlated with control signal and production parameter data obtained from control system 1202 of robotic panel assembly cell 1201A. In one embodiment, the quality parameter data and control signal and production parameter data are forwarded to quality analysis and feedback cell 301 for analyzing the quality of cured layered wood product panels. Based on this analysis, the control signals sent from control system 1202 of robotic panel assembly cell 1201A to the one or more veneer handling robots, the one or more core handling robots, and the one or more glue application robots is adjusted in order to improve the quality of subsequent cured layered wood product panels.

[0509] In one embodiment, the quality analysis and feedback cell 1301 includes an artificial intelligence module (not shown). In one embodiment, the quality analysis and feedback cell 1301 obtains the quality parameter data from the quality analysis of multiple cured layered wood product panels and correlates the quality parameter data associated with each cured layered wood product panel and the control signal and production parameter data associated with the control signals generated by control system 1202 used to control the one or more veneer handling robots, the one or more glue application robots, and the one or more core handling robots used to produce the cured layered wood product panel.

[0510] In one embodiment, the correlated quality data and control signal and production parameter data is then used as training data to generate a trained artificial intelligence module. In one embodiment, the trained artificial intelligence module is then used adjust the control signals used to control the one or more veneer handling robots, the one or more glue application robots, and the one or more core handling robots automatically for subsequent green layered wood product panel stack production.

[0511] As discussed above, embodiments of the present disclosure provide an effective and efficient technical solution to the long-standing technical problem of providing a method and system for producing layered wood products that is more consistent, more effective, less expensive to operate and more efficient than prior art methods.

[0512] The innovations disclosed herein are described in the general context of computer-executable instructions, such as those included in program modules, being executed in a computing system on a target real or virtual processor. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Computer-executable instructions for program modules may be executed within a local or distributed computing system.

[0513] For the sake of presentation, the detailed description uses terms like “determine” and “use” to describe computer operations in a computing system. These terms are high-level abstractions for operations performed by a computer and should not be confused with acts performed by a human being. The actual computer operations corresponding to these terms vary depending on implementation.

[0514] For purposes of this description, certain aspects, advantages, and novel features of the embodiments of this disclosure are described herein. The disclosed methods, apparatus, and systems should not be construed as being limiting in any way. Instead, the present disclosure is directed toward all novel and nonobvious features and aspects of the various disclosed embodiments, alone and in various combinations and sub-combinations with one another. The methods, apparatus, and systems are not limited to any specific aspect or feature or combination thereof, nor do the disclosed embodiments require that any one or more specific advantages be present, or problems be solved.

[0515] Although the operations of some of the disclosed embodiments are described in a particular, sequential order for convenient presentation, it should be understood that this manner of description encompasses rearrangement, unless a particular ordering is required by specific language set forth below. For example, operations described sequentially may in some cases be rearranged or performed concurrently. Moreover, for the sake of simplicity, the attached figures may not show the various ways in which the disclosed methods can be used in conjunction with other methods. Additionally, the description sometimes uses terms like “provide” or “achieve” to describe the disclosed methods. These terms may be high-level descriptions of the actual operations that are performed. The actual operations that correspond to these terms may vary depending on the particular implementation.

[0516] As used in this application and in the claims, the singular forms “a,” “an,” and “the” include the plural forms unless the context clearly dictates otherwise. Additionally, the term “includes” means “comprises.” Further, the terms “coupled” and “associated” generally mean electrically, electromagnetically, and/or physically (e.g., mechanically, or chemically) coupled or linked and does not exclude the presence of intermediate elements between the coupled or associated items absent specific contrary language.

[0517] As used herein, operations that occur “simultaneously” or “concurrently” occur generally at the same time as one another, although delays in the occurrence of one operation relative to the other due to, for example, spacing, play or backlash between components in a mechanical linkage such as threads, gears, etc., are expressly within the scope of the above terms, absent specific contrary language.

[0518] Any of the computer-executable instructions for implementing the disclosed techniques as well as any data created and used during implementation of the disclosed embodiments can be stored on one or more computer-readable storage media (e.g., non-transitory computer-readable media). The computer-executable instructions can be part of, for example, a dedicated software application or a software application that is accessed or downloaded via a web browser or other software application (such as a remote computing application). Such software can be executed, for example, on a single local computer (e.g., any suitable commercially available computer) or in a network environment (e.g., via the Internet, a wide-area network, a local-area network, a client-server network (such as a cloud computing network), or other such network) using one or more network computers.

[0519] For clarity, only certain selected aspects of the software-based implementations are described. Other details that are well known in the art are omitted. For example, it should be understood that the disclosed technology is not limited to any specific computer language or program. For instance, the disclosed technology can be implemented by software written in C++, Java, Perl, JavaScript, Adobe Flash, or any other suitable programming language. Likewise, the disclosed technology is not limited to any particular computer or type of hardware. Certain details of suitable computers and hardware are well known and need not be set forth in detail in this disclosure.

[0520] Furthermore, any of the software-based embodiments (comprising, for example, computer-executable instructions for causing a computer to perform any of the disclosed methods) can be uploaded, downloaded, or remotely accessed through a suitable communication means. Such suitable communication means include, for example, the Internet, the World Wide Web, an intranet, software applications, cable (including fiber optic cable), magnetic communications, electromagnetic communications (including RF, microwave, and infrared communications), electronic communications, or other such communication means.

[0521] In view of the many possible embodiments to which the principles of the disclosed technology may be applied, it should be recognized that the illustrated embodiments are only preferred examples of the disclosed technology and should not be taken as limiting the scope of the disclosed technology. Rather, the scope of the disclosure is at least as broad as the following claims. We therefore claim all that comes within the scope of these claims.

[0522] Therefore, numerous variations, whether explicitly provided for by the specification or implied by the specification or not, may be implemented by one of skill in the art in view of this disclosure.